< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 631 in Layer 5

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: 2.3474. Min Range: -2.3474

Max Act: 2.3474. Min Act: -0.1700

Data Index: 783987 (Open Web Text)

Max Activating Token Index: 441

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.3474. Min Range: -2.3474

Max Act: 2.3249. Min Act: -0.1700

Data Index: 7153385 (Open Web Text)

Max Activating Token Index: 152

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.3474. Min Range: -2.3474

Max Act: 2.2982. Min Act: -0.1700

Data Index: 7952867 (Open Web Text)

Max Activating Token Index: 630

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.3474. Min Range: -2.3474

Max Act: 2.2844. Min Act: -0.1700

Data Index: 8125652 (Open Web Text)

Max Activating Token Index: 490

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.3474. Min Range: -2.3474

Max Act: 2.3054. Min Act: -0.1700

Data Index: 7298263 (Open Web Text)

Max Activating Token Index: 74

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.3474. Min Range: -2.3474

Max Act: 2.2771. Min Act: -0.1700

Data Index: 7329884 (Open Web Text)

Max Activating Token Index: 322

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.3474. Min Range: -2.3474

Max Act: 2.2645. Min Act: -0.1700

Data Index: 1504349 (Open Web Text)

Max Activating Token Index: 730

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.3474. Min Range: -2.3474

Max Act: 2.2829. Min Act: -0.1700

Data Index: 7081167 (Open Web Text)

Max Activating Token Index: 997

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.3474. Min Range: -2.3474

Max Act: 2.2553. Min Act: -0.1700

Data Index: 7020195 (Open Web Text)

Max Activating Token Index: 970

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.3474. Min Range: -2.3474

Max Act: 2.2528. Min Act: -0.1700

Data Index: 4018448 (Open Web Text)

Max Activating Token Index: 154

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.3474. Min Range: -2.3474

Max Act: 2.2545. Min Act: -0.1700

Data Index: 2861537 (Open Web Text)

Max Activating Token Index: 837

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.3474. Min Range: -2.3474

Max Act: 2.2457. Min Act: -0.1700

Data Index: 2283930 (Open Web Text)

Max Activating Token Index: 248

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.3474. Min Range: -2.3474

Max Act: 2.2466. Min Act: -0.1700

Data Index: 2298242 (Open Web Text)

Max Activating Token Index: 380

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.3474. Min Range: -2.3474

Max Act: 2.2611. Min Act: -0.1700

Data Index: 6798375 (Open Web Text)

Max Activating Token Index: 489

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.3474. Min Range: -2.3474

Max Act: 2.2353. Min Act: -0.1700

Data Index: 1053229 (Open Web Text)

Max Activating Token Index: 205

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.3474. Min Range: -2.3474

Max Act: 2.2493. Min Act: -0.1700

Data Index: 869508 (Open Web Text)

Max Activating Token Index: 873

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.3474. Min Range: -2.3474

Max Act: 2.2482. Min Act: -0.1700

Data Index: 2304757 (Open Web Text)

Max Activating Token Index: 385

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.3474. Min Range: -2.3474

Max Act: 2.2220. Min Act: -0.1700

Data Index: 1066795 (Open Web Text)

Max Activating Token Index: 283

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.3474. Min Range: -2.3474

Max Act: 2.2226. Min Act: -0.1700

Data Index: 3271842 (Open Web Text)

Max Activating Token Index: 592

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.3474. Min Range: -2.3474

Max Act: 2.2197. Min Act: -0.1700

Data Index: 1722480 (Open Web Text)

Max Activating Token Index: 876

Click toggle to see full text

Truncated

Full Text #19