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

Dataset: Open Web Text

Neuron 688 in Layer 6

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: 3.1445. Min Range: -3.1445

Max Act: 3.1445. Min Act: -0.1700

Data Index: 1760024 (Open Web Text)

Max Activating Token Index: 1011

Text #1

Max Range: 3.1445. Min Range: -3.1445

Max Act: 3.0171. Min Act: -0.1700

Data Index: 6395505 (Open Web Text)

Max Activating Token Index: 295

Text #2

Max Range: 3.1445. Min Range: -3.1445

Max Act: 3.0379. Min Act: -0.1700

Data Index: 4420900 (Open Web Text)

Max Activating Token Index: 948

Text #3

Max Range: 3.1445. Min Range: -3.1445

Max Act: 2.9349. Min Act: -0.1700

Data Index: 4609278 (Open Web Text)

Max Activating Token Index: 856

Text #4

Max Range: 3.1445. Min Range: -3.1445

Max Act: 2.9204. Min Act: -0.1700

Data Index: 2370163 (Open Web Text)

Max Activating Token Index: 671

Text #5

Max Range: 3.1445. Min Range: -3.1445

Max Act: 2.8705. Min Act: -0.1700

Data Index: 1738313 (Open Web Text)

Max Activating Token Index: 814

Text #6

Max Range: 3.1445. Min Range: -3.1445

Max Act: 2.9037. Min Act: -0.1700

Data Index: 3839435 (Open Web Text)

Max Activating Token Index: 374

Text #7

Max Range: 3.1445. Min Range: -3.1445

Max Act: 2.9171. Min Act: -0.1700

Data Index: 7013957 (Open Web Text)

Max Activating Token Index: 830

Text #8

Max Range: 3.1445. Min Range: -3.1445

Max Act: 2.8909. Min Act: -0.1700

Data Index: 1483936 (Open Web Text)

Max Activating Token Index: 580

Text #9

Max Range: 3.1445. Min Range: -3.1445

Max Act: 2.8979. Min Act: -0.1700

Data Index: 115863 (Open Web Text)

Max Activating Token Index: 137

Text #10

Max Range: 3.1445. Min Range: -3.1445

Max Act: 2.8587. Min Act: -0.1700

Data Index: 2388364 (Open Web Text)

Max Activating Token Index: 816

Text #11

Max Range: 3.1445. Min Range: -3.1445

Max Act: 2.8398. Min Act: -0.1700

Data Index: 7060569 (Open Web Text)

Max Activating Token Index: 469

Text #12

Max Range: 3.1445. Min Range: -3.1445

Max Act: 2.8540. Min Act: -0.1700

Data Index: 1487556 (Open Web Text)

Max Activating Token Index: 207

Text #13

Max Range: 3.1445. Min Range: -3.1445

Max Act: 2.8728. Min Act: -0.1700

Data Index: 1050778 (Open Web Text)

Max Activating Token Index: 108

Text #14

Max Range: 3.1445. Min Range: -3.1445

Max Act: 2.8422. Min Act: -0.1700

Data Index: 6722330 (Open Web Text)

Max Activating Token Index: 968

Text #15

Max Range: 3.1445. Min Range: -3.1445

Max Act: 2.8608. Min Act: -0.1700

Data Index: 8134298 (Open Web Text)

Max Activating Token Index: 337

Text #16

Max Range: 3.1445. Min Range: -3.1445

Max Act: 2.8431. Min Act: -0.1700

Data Index: 3266904 (Open Web Text)

Max Activating Token Index: 843

Text #17

Max Range: 3.1445. Min Range: -3.1445

Max Act: 2.8367. Min Act: -0.1700

Data Index: 1430973 (Open Web Text)

Max Activating Token Index: 139

Text #18

Max Range: 3.1445. Min Range: -3.1445

Max Act: 2.7912. Min Act: -0.1700

Data Index: 6035071 (Open Web Text)

Max Activating Token Index: 139

Text #19

Max Range: 3.1445. Min Range: -3.1445

Max Act: 2.8405. Min Act: -0.1700

Data Index: 8796990 (Open Web Text)

Max Activating Token Index: 277