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

Dataset: Open Web Text

Neuron 240 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: 3.5574. Min Range: -3.5574

Max Act: 3.5574. Min Act: -0.1700

Data Index: 5146299 (Open Web Text)

Max Activating Token Index: 795

Text #1

Max Range: 3.5574. Min Range: -3.5574

Max Act: 3.3881. Min Act: -0.1700

Data Index: 8307430 (Open Web Text)

Max Activating Token Index: 708

Text #2

Max Range: 3.5574. Min Range: -3.5574

Max Act: 3.3991. Min Act: -0.1700

Data Index: 6958533 (Open Web Text)

Max Activating Token Index: 353

Text #3

Max Range: 3.5574. Min Range: -3.5574

Max Act: 3.3730. Min Act: -0.1700

Data Index: 4692278 (Open Web Text)

Max Activating Token Index: 387

Text #4

Max Range: 3.5574. Min Range: -3.5574

Max Act: 3.3804. Min Act: -0.1700

Data Index: 7109326 (Open Web Text)

Max Activating Token Index: 452

Text #5

Max Range: 3.5574. Min Range: -3.5574

Max Act: 3.3889. Min Act: -0.1700

Data Index: 5045582 (Open Web Text)

Max Activating Token Index: 213

Text #6

Max Range: 3.5574. Min Range: -3.5574

Max Act: 3.3686. Min Act: -0.1700

Data Index: 6134483 (Open Web Text)

Max Activating Token Index: 911

Text #7

Max Range: 3.5574. Min Range: -3.5574

Max Act: 3.3536. Min Act: -0.1700

Data Index: 6559818 (Open Web Text)

Max Activating Token Index: 727

Text #8

Max Range: 3.5574. Min Range: -3.5574

Max Act: 3.3657. Min Act: -0.1700

Data Index: 4382476 (Open Web Text)

Max Activating Token Index: 326

Text #9

Max Range: 3.5574. Min Range: -3.5574

Max Act: 3.3637. Min Act: -0.1700

Data Index: 4194220 (Open Web Text)

Max Activating Token Index: 462

Text #10

Max Range: 3.5574. Min Range: -3.5574

Max Act: 3.3520. Min Act: -0.1700

Data Index: 3071003 (Open Web Text)

Max Activating Token Index: 177

Text #11

Max Range: 3.5574. Min Range: -3.5574

Max Act: 3.3263. Min Act: -0.1700

Data Index: 6270121 (Open Web Text)

Max Activating Token Index: 362

Text #12

Max Range: 3.5574. Min Range: -3.5574

Max Act: 3.3466. Min Act: -0.1700

Data Index: 5752367 (Open Web Text)

Max Activating Token Index: 834

Text #13

Max Range: 3.5574. Min Range: -3.5574

Max Act: 3.3242. Min Act: -0.1700

Data Index: 8663577 (Open Web Text)

Max Activating Token Index: 406

Text #14

Max Range: 3.5574. Min Range: -3.5574

Max Act: 3.3314. Min Act: -0.1700

Data Index: 3831784 (Open Web Text)

Max Activating Token Index: 202

Text #15

Max Range: 3.5574. Min Range: -3.5574

Max Act: 3.3255. Min Act: -0.1700

Data Index: 5007320 (Open Web Text)

Max Activating Token Index: 505

Text #16

Max Range: 3.5574. Min Range: -3.5574

Max Act: 3.3111. Min Act: -0.1700

Data Index: 8585393 (Open Web Text)

Max Activating Token Index: 583

Text #17

Max Range: 3.5574. Min Range: -3.5574

Max Act: 3.3177. Min Act: -0.1700

Data Index: 1401084 (Open Web Text)

Max Activating Token Index: 237

Text #18

Max Range: 3.5574. Min Range: -3.5574

Max Act: 3.3204. Min Act: -0.1700

Data Index: 4739746 (Open Web Text)

Max Activating Token Index: 193

Text #19

Max Range: 3.5574. Min Range: -3.5574

Max Act: 3.2913. Min Act: -0.1700

Data Index: 3547618 (Open Web Text)

Max Activating Token Index: 84