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

Dataset: Open Web Text

Neuron 2933 in Layer 4

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: 4.4361. Min Range: -4.4361

Max Act: 4.4077. Min Act: -0.1700

Data Index: 6455246 (Open Web Text)

Max Activating Token Index: 606

Text #1

Max Range: 4.4361. Min Range: -4.4361

Max Act: 4.4361. Min Act: -0.1700

Data Index: 1859652 (Open Web Text)

Max Activating Token Index: 454

Text #2

Max Range: 4.4361. Min Range: -4.4361

Max Act: 4.2893. Min Act: -0.1700

Data Index: 7472199 (Open Web Text)

Max Activating Token Index: 322

Text #3

Max Range: 4.4361. Min Range: -4.4361

Max Act: 4.2736. Min Act: -0.1700

Data Index: 174202 (Open Web Text)

Max Activating Token Index: 408

Text #4

Max Range: 4.4361. Min Range: -4.4361

Max Act: 4.2443. Min Act: -0.1700

Data Index: 1502220 (Open Web Text)

Max Activating Token Index: 566

Text #5

Max Range: 4.4361. Min Range: -4.4361

Max Act: 4.2046. Min Act: -0.1700

Data Index: 6904413 (Open Web Text)

Max Activating Token Index: 167

Text #6

Max Range: 4.4361. Min Range: -4.4361

Max Act: 4.1944. Min Act: -0.1700

Data Index: 6717533 (Open Web Text)

Max Activating Token Index: 374

Text #7

Max Range: 4.4361. Min Range: -4.4361

Max Act: 4.2175. Min Act: -0.1700

Data Index: 5808629 (Open Web Text)

Max Activating Token Index: 644

Text #8

Max Range: 4.4361. Min Range: -4.4361

Max Act: 4.1474. Min Act: -0.1700

Data Index: 5220027 (Open Web Text)

Max Activating Token Index: 515

Text #9

Max Range: 4.4361. Min Range: -4.4361

Max Act: 4.1381. Min Act: -0.1700

Data Index: 2323302 (Open Web Text)

Max Activating Token Index: 418

Text #10

Max Range: 4.4361. Min Range: -4.4361

Max Act: 4.1373. Min Act: -0.1700

Data Index: 7431498 (Open Web Text)

Max Activating Token Index: 175

Text #11

Max Range: 4.4361. Min Range: -4.4361

Max Act: 4.1373. Min Act: -0.1700

Data Index: 2522812 (Open Web Text)

Max Activating Token Index: 862

Text #12

Max Range: 4.4361. Min Range: -4.4361

Max Act: 4.1543. Min Act: -0.1700

Data Index: 8685918 (Open Web Text)

Max Activating Token Index: 251

Text #13

Max Range: 4.4361. Min Range: -4.4361

Max Act: 4.1304. Min Act: -0.1700

Data Index: 5907141 (Open Web Text)

Max Activating Token Index: 473

Text #14

Max Range: 4.4361. Min Range: -4.4361

Max Act: 4.0976. Min Act: -0.1700

Data Index: 4582523 (Open Web Text)

Max Activating Token Index: 419

Text #15

Max Range: 4.4361. Min Range: -4.4361

Max Act: 4.1024. Min Act: -0.1700

Data Index: 1679836 (Open Web Text)

Max Activating Token Index: 437

Text #16

Max Range: 4.4361. Min Range: -4.4361

Max Act: 4.0270. Min Act: -0.1700

Data Index: 3140051 (Open Web Text)

Max Activating Token Index: 337

Text #17

Max Range: 4.4361. Min Range: -4.4361

Max Act: 4.0955. Min Act: -0.1700

Data Index: 7362232 (Open Web Text)

Max Activating Token Index: 580

Text #18

Max Range: 4.4361. Min Range: -4.4361

Max Act: 4.0759. Min Act: -0.1700

Data Index: 1346339 (Open Web Text)

Max Activating Token Index: 367

Text #19

Max Range: 4.4361. Min Range: -4.4361

Max Act: 4.0564. Min Act: -0.1700

Data Index: 7435372 (Open Web Text)

Max Activating Token Index: 661