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

Dataset: Open Web Text

Neuron 328 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: 1.7294. Min Range: -1.7294

Max Act: 1.7213. Min Act: -0.1700

Data Index: 7007644 (Open Web Text)

Max Activating Token Index: 550

Text #1

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.7294. Min Act: -0.1700

Data Index: 444419 (Open Web Text)

Max Activating Token Index: 394

Text #2

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.7233. Min Act: -0.1700

Data Index: 2129434 (Open Web Text)

Max Activating Token Index: 672

Text #3

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.7196. Min Act: -0.1700

Data Index: 2126506 (Open Web Text)

Max Activating Token Index: 224

Text #4

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.7046. Min Act: -0.1700

Data Index: 6764954 (Open Web Text)

Max Activating Token Index: 127

Text #5

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.6891. Min Act: -0.1700

Data Index: 1460744 (Open Web Text)

Max Activating Token Index: 204

Text #6

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.6870. Min Act: -0.1700

Data Index: 1266852 (Open Web Text)

Max Activating Token Index: 360

Text #7

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.6683. Min Act: -0.1700

Data Index: 3137796 (Open Web Text)

Max Activating Token Index: 689

Text #8

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.6705. Min Act: -0.1700

Data Index: 7047565 (Open Web Text)

Max Activating Token Index: 283

Text #9

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.6674. Min Act: -0.1700

Data Index: 3099195 (Open Web Text)

Max Activating Token Index: 186

Text #10

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.6600. Min Act: -0.1700

Data Index: 5654440 (Open Web Text)

Max Activating Token Index: 91

Text #11

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.6496. Min Act: -0.1700

Data Index: 1604805 (Open Web Text)

Max Activating Token Index: 686

Text #12

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.6471. Min Act: -0.1700

Data Index: 7026285 (Open Web Text)

Max Activating Token Index: 488

Text #13

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.6523. Min Act: -0.1700

Data Index: 4632354 (Open Web Text)

Max Activating Token Index: 686

Text #14

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.6391. Min Act: -0.1700

Data Index: 6363797 (Open Web Text)

Max Activating Token Index: 482

Text #15

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.6421. Min Act: -0.1700

Data Index: 1507861 (Open Web Text)

Max Activating Token Index: 348

Text #16

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.6384. Min Act: -0.1700

Data Index: 4007408 (Open Web Text)

Max Activating Token Index: 596

Text #17

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.6389. Min Act: -0.1700

Data Index: 6018687 (Open Web Text)

Max Activating Token Index: 729

Text #18

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.6485. Min Act: -0.1700

Data Index: 518287 (Open Web Text)

Max Activating Token Index: 201

Text #19

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.6264. Min Act: -0.1700

Data Index: 6345100 (Open Web Text)

Max Activating Token Index: 644