< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 1376 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: 2.1190. Min Range: -2.1190

Max Act: 2.1190. Min Act: -0.1700

Data Index: 5240540 (Open Web Text)

Max Activating Token Index: 220

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.1190. Min Range: -2.1190

Max Act: 2.0604. Min Act: -0.1700

Data Index: 859912 (Open Web Text)

Max Activating Token Index: 645

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.1190. Min Range: -2.1190

Max Act: 2.0444. Min Act: -0.1700

Data Index: 3165700 (Open Web Text)

Max Activating Token Index: 158

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.1190. Min Range: -2.1190

Max Act: 2.0248. Min Act: -0.1700

Data Index: 5946346 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.1190. Min Range: -2.1190

Max Act: 2.0440. Min Act: -0.1700

Data Index: 252244 (Open Web Text)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.1190. Min Range: -2.1190

Max Act: 1.9949. Min Act: -0.1700

Data Index: 6903970 (Open Web Text)

Max Activating Token Index: 741

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.1190. Min Range: -2.1190

Max Act: 1.9829. Min Act: -0.1700

Data Index: 3857083 (Open Web Text)

Max Activating Token Index: 571

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.1190. Min Range: -2.1190

Max Act: 1.9822. Min Act: -0.1700

Data Index: 2119125 (Open Web Text)

Max Activating Token Index: 534

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.1190. Min Range: -2.1190

Max Act: 1.9991. Min Act: -0.1700

Data Index: 3553442 (Open Web Text)

Max Activating Token Index: 12

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.1190. Min Range: -2.1190

Max Act: 1.9817. Min Act: -0.1700

Data Index: 6444563 (Open Web Text)

Max Activating Token Index: 906

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.1190. Min Range: -2.1190

Max Act: 1.9843. Min Act: -0.1700

Data Index: 5104000 (Open Web Text)

Max Activating Token Index: 442

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.1190. Min Range: -2.1190

Max Act: 1.9692. Min Act: -0.1700

Data Index: 3452274 (Open Web Text)

Max Activating Token Index: 184

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.1190. Min Range: -2.1190

Max Act: 1.9912. Min Act: -0.1700

Data Index: 5247263 (Open Web Text)

Max Activating Token Index: 815

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.1190. Min Range: -2.1190

Max Act: 1.9618. Min Act: -0.1700

Data Index: 7927281 (Open Web Text)

Max Activating Token Index: 672

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.1190. Min Range: -2.1190

Max Act: 1.9700. Min Act: -0.1700

Data Index: 8536391 (Open Web Text)

Max Activating Token Index: 446

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.1190. Min Range: -2.1190

Max Act: 1.9590. Min Act: -0.1700

Data Index: 1418529 (Open Web Text)

Max Activating Token Index: 643

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.1190. Min Range: -2.1190

Max Act: 1.9479. Min Act: -0.1700

Data Index: 564223 (Open Web Text)

Max Activating Token Index: 613

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.1190. Min Range: -2.1190

Max Act: 1.9555. Min Act: -0.1700

Data Index: 3376583 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.1190. Min Range: -2.1190

Max Act: 1.9383. Min Act: -0.1700

Data Index: 1503468 (Open Web Text)

Max Activating Token Index: 803

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.1190. Min Range: -2.1190

Max Act: 1.9521. Min Act: -0.1700

Data Index: 2436361 (Open Web Text)

Max Activating Token Index: 498

Click toggle to see full text

Truncated

Full Text #19