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

Dataset: Open Web Text

Neuron 419 in Layer 1

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: 0.9158. Min Range: -0.9158

Max Act: 0.9158. Min Act: -0.1292

Data Index: 359346 (Open Web Text)

Max Activating Token Index: 919

Text #1

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.8982. Min Act: -0.1292

Data Index: 359349 (Open Web Text)

Max Activating Token Index: 937

Text #2

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.8946. Min Act: -0.1292

Data Index: 359354 (Open Web Text)

Max Activating Token Index: 918

Text #3

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.8840. Min Act: -0.0997

Data Index: 359339 (Open Web Text)

Max Activating Token Index: 911

Text #4

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.8809. Min Act: -0.1203

Data Index: 359337 (Open Web Text)

Max Activating Token Index: 911

Text #5

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.8787. Min Act: -0.0583

Data Index: 359344 (Open Web Text)

Max Activating Token Index: 928

Text #6

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.8669. Min Act: -0.1386

Data Index: 359334 (Open Web Text)

Max Activating Token Index: 914

Text #7

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.8589. Min Act: -0.1292

Data Index: 359350 (Open Web Text)

Max Activating Token Index: 892

Text #8

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.8478. Min Act: -0.1441

Data Index: 1983715 (Open Web Text)

Max Activating Token Index: 923

Text #9

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.8441. Min Act: -0.1471

Data Index: 373504 (Open Web Text)

Max Activating Token Index: 927

Text #10

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.8421. Min Act: -0.1358

Data Index: 7843148 (Open Web Text)

Max Activating Token Index: 679

Text #11

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.8456. Min Act: -0.1428

Data Index: 359345 (Open Web Text)

Max Activating Token Index: 893

Text #12

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.8414. Min Act: -0.1293

Data Index: 359348 (Open Web Text)

Max Activating Token Index: 901

Text #13

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.8329. Min Act: -0.1332

Data Index: 7893893 (Open Web Text)

Max Activating Token Index: 693

Text #14

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.8373. Min Act: -0.1045

Data Index: 359343 (Open Web Text)

Max Activating Token Index: 925

Text #15

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.8382. Min Act: -0.0597

Data Index: 359336 (Open Web Text)

Max Activating Token Index: 418

Text #16

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.8251. Min Act: -0.1029

Data Index: 1738011 (Open Web Text)

Max Activating Token Index: 673

Text #17

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.8235. Min Act: -0.1099

Data Index: 4102293 (Open Web Text)

Max Activating Token Index: 699

Text #18

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.8340. Min Act: -0.1358

Data Index: 669094 (Open Web Text)

Max Activating Token Index: 734

Text #19

Max Range: 0.9158. Min Range: -0.9158

Max Act: 0.8232. Min Act: -0.1292

Data Index: 359355 (Open Web Text)

Max Activating Token Index: 850