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

Dataset: Open Web Text

Neuron 1304 in Layer 3

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: 3.0231. Min Range: -3.0231

Max Act: 3.0231. Min Act: -0.1700

Data Index: 8510054 (Open Web Text)

Max Activating Token Index: 409

Text #1

Max Range: 3.0231. Min Range: -3.0231

Max Act: 3.0067. Min Act: -0.1700

Data Index: 6551439 (Open Web Text)

Max Activating Token Index: 391

Text #2

Max Range: 3.0231. Min Range: -3.0231

Max Act: 2.9777. Min Act: -0.1700

Data Index: 6124704 (Open Web Text)

Max Activating Token Index: 256

Text #3

Max Range: 3.0231. Min Range: -3.0231

Max Act: 2.9863. Min Act: -0.1700

Data Index: 1567922 (Open Web Text)

Max Activating Token Index: 167

Text #4

Max Range: 3.0231. Min Range: -3.0231

Max Act: 2.9660. Min Act: -0.1700

Data Index: 652904 (Open Web Text)

Max Activating Token Index: 945

Text #5

Max Range: 3.0231. Min Range: -3.0231

Max Act: 2.9713. Min Act: -0.1700

Data Index: 4071857 (Open Web Text)

Max Activating Token Index: 539

Text #6

Max Range: 3.0231. Min Range: -3.0231

Max Act: 2.9639. Min Act: -0.1700

Data Index: 8176216 (Open Web Text)

Max Activating Token Index: 33

Text #7

Max Range: 3.0231. Min Range: -3.0231

Max Act: 2.9493. Min Act: -0.1700

Data Index: 2160488 (Open Web Text)

Max Activating Token Index: 814

Text #8

Max Range: 3.0231. Min Range: -3.0231

Max Act: 2.9371. Min Act: -0.1700

Data Index: 3500583 (Open Web Text)

Max Activating Token Index: 651

Text #9

Max Range: 3.0231. Min Range: -3.0231

Max Act: 2.9523. Min Act: -0.1700

Data Index: 5709009 (Open Web Text)

Max Activating Token Index: 373

Text #10

Max Range: 3.0231. Min Range: -3.0231

Max Act: 2.9471. Min Act: -0.1700

Data Index: 2724247 (Open Web Text)

Max Activating Token Index: 278

Text #11

Max Range: 3.0231. Min Range: -3.0231

Max Act: 2.9404. Min Act: -0.1700

Data Index: 4318751 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 3.0231. Min Range: -3.0231

Max Act: 2.9389. Min Act: -0.1700

Data Index: 6431169 (Open Web Text)

Max Activating Token Index: 438

Text #13

Max Range: 3.0231. Min Range: -3.0231

Max Act: 2.9474. Min Act: -0.1700

Data Index: 8399463 (Open Web Text)

Max Activating Token Index: 834

Text #14

Max Range: 3.0231. Min Range: -3.0231

Max Act: 2.9356. Min Act: -0.1700

Data Index: 6709201 (Open Web Text)

Max Activating Token Index: 156

Text #15

Max Range: 3.0231. Min Range: -3.0231

Max Act: 2.9475. Min Act: -0.1700

Data Index: 135062 (Open Web Text)

Max Activating Token Index: 152

Text #16

Max Range: 3.0231. Min Range: -3.0231

Max Act: 2.9426. Min Act: -0.1700

Data Index: 2856922 (Open Web Text)

Max Activating Token Index: 793

Text #17

Max Range: 3.0231. Min Range: -3.0231

Max Act: 2.9342. Min Act: -0.1700

Data Index: 4392746 (Open Web Text)

Max Activating Token Index: 390

Text #18

Max Range: 3.0231. Min Range: -3.0231

Max Act: 2.9212. Min Act: -0.1700

Data Index: 5202059 (Open Web Text)

Max Activating Token Index: 21

Text #19

Max Range: 3.0231. Min Range: -3.0231

Max Act: 2.9157. Min Act: -0.1700

Data Index: 997188 (Open Web Text)

Max Activating Token Index: 11