< Prev | Home | Model | Random | Next >

Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 233 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 2.3815. Min Range: -2.3815

Max Act: 2.3815. Min Act: -0.1700

Data Index: 124139 (Open Web Text)

Max Activating Token Index: 613

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.3815. Min Range: -2.3815

Max Act: 2.2859. Min Act: -0.1700

Data Index: 2614346 (Open Web Text)

Max Activating Token Index: 670

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.3815. Min Range: -2.3815

Max Act: 2.2957. Min Act: -0.1700

Data Index: 2611515 (Open Web Text)

Max Activating Token Index: 486

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.3815. Min Range: -2.3815

Max Act: 2.2887. Min Act: -0.1700

Data Index: 7335537 (Open Web Text)

Max Activating Token Index: 941

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.3815. Min Range: -2.3815

Max Act: 2.2773. Min Act: -0.1700

Data Index: 7043502 (Open Web Text)

Max Activating Token Index: 793

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.3815. Min Range: -2.3815

Max Act: 2.2721. Min Act: -0.1700

Data Index: 2400962 (Open Web Text)

Max Activating Token Index: 181

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.3815. Min Range: -2.3815

Max Act: 2.2626. Min Act: -0.1700

Data Index: 1176291 (Open Web Text)

Max Activating Token Index: 986

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.3815. Min Range: -2.3815

Max Act: 2.2549. Min Act: -0.1700

Data Index: 2586782 (Open Web Text)

Max Activating Token Index: 27

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.3815. Min Range: -2.3815

Max Act: 2.2487. Min Act: -0.1700

Data Index: 3872588 (Open Web Text)

Max Activating Token Index: 548

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.3815. Min Range: -2.3815

Max Act: 2.2583. Min Act: -0.1700

Data Index: 8472520 (Open Web Text)

Max Activating Token Index: 543

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.3815. Min Range: -2.3815

Max Act: 2.2548. Min Act: -0.1700

Data Index: 6921174 (Open Web Text)

Max Activating Token Index: 141

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.3815. Min Range: -2.3815

Max Act: 2.2232. Min Act: -0.1700

Data Index: 5903542 (Open Web Text)

Max Activating Token Index: 896

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.3815. Min Range: -2.3815

Max Act: 2.2346. Min Act: -0.1700

Data Index: 3438463 (Open Web Text)

Max Activating Token Index: 604

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.3815. Min Range: -2.3815

Max Act: 2.2328. Min Act: -0.1700

Data Index: 1876103 (Open Web Text)

Max Activating Token Index: 700

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.3815. Min Range: -2.3815

Max Act: 2.2382. Min Act: -0.1700

Data Index: 7738732 (Open Web Text)

Max Activating Token Index: 804

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.3815. Min Range: -2.3815

Max Act: 2.2415. Min Act: -0.1700

Data Index: 3767809 (Open Web Text)

Max Activating Token Index: 848

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.3815. Min Range: -2.3815

Max Act: 2.2404. Min Act: -0.1700

Data Index: 8100060 (Open Web Text)

Max Activating Token Index: 488

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.3815. Min Range: -2.3815

Max Act: 2.2387. Min Act: -0.1700

Data Index: 2199387 (Open Web Text)

Max Activating Token Index: 926

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.3815. Min Range: -2.3815

Max Act: 2.2294. Min Act: -0.1700

Data Index: 1413508 (Open Web Text)

Max Activating Token Index: 826

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.3815. Min Range: -2.3815

Max Act: 2.2348. Min Act: -0.1700

Data Index: 6026945 (Open Web Text)

Max Activating Token Index: 672

Click toggle to see full text

Truncated

Full Text #19