< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 593 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: 2.3313. Min Range: -2.3313

Max Act: 2.3313. Min Act: -0.1700

Data Index: 2607349 (Open Web Text)

Max Activating Token Index: 298

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.3313. Min Range: -2.3313

Max Act: 2.3304. Min Act: -0.1700

Data Index: 82654 (Open Web Text)

Max Activating Token Index: 564

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.3313. Min Range: -2.3313

Max Act: 2.3268. Min Act: -0.1700

Data Index: 7772276 (Open Web Text)

Max Activating Token Index: 769

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.3313. Min Range: -2.3313

Max Act: 2.3202. Min Act: -0.1700

Data Index: 466868 (Open Web Text)

Max Activating Token Index: 481

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.3313. Min Range: -2.3313

Max Act: 2.2897. Min Act: -0.1700

Data Index: 1239188 (Open Web Text)

Max Activating Token Index: 375

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.3313. Min Range: -2.3313

Max Act: 2.3189. Min Act: -0.1700

Data Index: 5192365 (Open Web Text)

Max Activating Token Index: 468

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.3313. Min Range: -2.3313

Max Act: 2.2945. Min Act: -0.1700

Data Index: 2311169 (Open Web Text)

Max Activating Token Index: 300

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.3313. Min Range: -2.3313

Max Act: 2.2939. Min Act: -0.1700

Data Index: 1862107 (Open Web Text)

Max Activating Token Index: 467

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.3313. Min Range: -2.3313

Max Act: 2.2951. Min Act: -0.1700

Data Index: 1609034 (Open Web Text)

Max Activating Token Index: 635

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.3313. Min Range: -2.3313

Max Act: 2.2751. Min Act: -0.1700

Data Index: 7873343 (Open Web Text)

Max Activating Token Index: 240

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.3313. Min Range: -2.3313

Max Act: 2.2916. Min Act: -0.1700

Data Index: 7330466 (Open Web Text)

Max Activating Token Index: 301

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.3313. Min Range: -2.3313

Max Act: 2.2761. Min Act: -0.1700

Data Index: 3490100 (Open Web Text)

Max Activating Token Index: 525

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.3313. Min Range: -2.3313

Max Act: 2.2811. Min Act: -0.1700

Data Index: 3710269 (Open Web Text)

Max Activating Token Index: 271

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.3313. Min Range: -2.3313

Max Act: 2.2677. Min Act: -0.1700

Data Index: 1291388 (Open Web Text)

Max Activating Token Index: 271

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.3313. Min Range: -2.3313

Max Act: 2.2788. Min Act: -0.1700

Data Index: 2194698 (Open Web Text)

Max Activating Token Index: 261

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.3313. Min Range: -2.3313

Max Act: 2.2830. Min Act: -0.1700

Data Index: 6302577 (Open Web Text)

Max Activating Token Index: 499

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.3313. Min Range: -2.3313

Max Act: 2.2829. Min Act: -0.1700

Data Index: 4791366 (Open Web Text)

Max Activating Token Index: 207

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.3313. Min Range: -2.3313

Max Act: 2.2654. Min Act: -0.1700

Data Index: 729120 (Open Web Text)

Max Activating Token Index: 276

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.3313. Min Range: -2.3313

Max Act: 2.2754. Min Act: -0.1700

Data Index: 1278528 (Open Web Text)

Max Activating Token Index: 221

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.3313. Min Range: -2.3313

Max Act: 2.2570. Min Act: -0.1700

Data Index: 6292333 (Open Web Text)

Max Activating Token Index: 901

Click toggle to see full text

Truncated

Full Text #19