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

Dataset: Open Web Text

Neuron 2005 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: 4.7396. Min Range: -4.7396

Max Act: 4.7035. Min Act: -0.1700

Data Index: 5783286 (Open Web Text)

Max Activating Token Index: 665

Text #1

Max Range: 4.7396. Min Range: -4.7396

Max Act: 4.7396. Min Act: -0.1700

Data Index: 5810254 (Open Web Text)

Max Activating Token Index: 382

Text #2

Max Range: 4.7396. Min Range: -4.7396

Max Act: 4.6932. Min Act: -0.1700

Data Index: 906085 (Open Web Text)

Max Activating Token Index: 939

Text #3

Max Range: 4.7396. Min Range: -4.7396

Max Act: 4.6221. Min Act: -0.1700

Data Index: 1142936 (Open Web Text)

Max Activating Token Index: 1015

Text #4

Max Range: 4.7396. Min Range: -4.7396

Max Act: 4.6345. Min Act: -0.1700

Data Index: 1588756 (Open Web Text)

Max Activating Token Index: 235

Text #5

Max Range: 4.7396. Min Range: -4.7396

Max Act: 4.6309. Min Act: -0.1700

Data Index: 1592921 (Open Web Text)

Max Activating Token Index: 124

Text #6

Max Range: 4.7396. Min Range: -4.7396

Max Act: 4.6533. Min Act: -0.1700

Data Index: 1594392 (Open Web Text)

Max Activating Token Index: 211

Text #7

Max Range: 4.7396. Min Range: -4.7396

Max Act: 4.6167. Min Act: -0.1700

Data Index: 4687602 (Open Web Text)

Max Activating Token Index: 117

Text #8

Max Range: 4.7396. Min Range: -4.7396

Max Act: 4.6126. Min Act: -0.1700

Data Index: 7341804 (Open Web Text)

Max Activating Token Index: 178

Text #9

Max Range: 4.7396. Min Range: -4.7396

Max Act: 4.5961. Min Act: -0.1700

Data Index: 3086845 (Open Web Text)

Max Activating Token Index: 756

Text #10

Max Range: 4.7396. Min Range: -4.7396

Max Act: 4.5872. Min Act: -0.1700

Data Index: 7318614 (Open Web Text)

Max Activating Token Index: 161

Text #11

Max Range: 4.7396. Min Range: -4.7396

Max Act: 4.6141. Min Act: -0.1700

Data Index: 3608648 (Open Web Text)

Max Activating Token Index: 494

Text #12

Max Range: 4.7396. Min Range: -4.7396

Max Act: 4.5885. Min Act: -0.1700

Data Index: 7172477 (Open Web Text)

Max Activating Token Index: 389

Text #13

Max Range: 4.7396. Min Range: -4.7396

Max Act: 4.6014. Min Act: -0.1700

Data Index: 4420995 (Open Web Text)

Max Activating Token Index: 1007

Text #14

Max Range: 4.7396. Min Range: -4.7396

Max Act: 4.6274. Min Act: -0.1700

Data Index: 2427297 (Open Web Text)

Max Activating Token Index: 972

Text #15

Max Range: 4.7396. Min Range: -4.7396

Max Act: 4.5703. Min Act: -0.1700

Data Index: 5183149 (Open Web Text)

Max Activating Token Index: 417

Text #16

Max Range: 4.7396. Min Range: -4.7396

Max Act: 4.6032. Min Act: -0.1700

Data Index: 5171486 (Open Web Text)

Max Activating Token Index: 825

Text #17

Max Range: 4.7396. Min Range: -4.7396

Max Act: 4.5425. Min Act: -0.1700

Data Index: 7065499 (Open Web Text)

Max Activating Token Index: 266

Text #18

Max Range: 4.7396. Min Range: -4.7396

Max Act: 4.5427. Min Act: -0.1700

Data Index: 3898931 (Open Web Text)

Max Activating Token Index: 829

Text #19

Max Range: 4.7396. Min Range: -4.7396

Max Act: 4.5752. Min Act: -0.1700

Data Index: 1550636 (Open Web Text)

Max Activating Token Index: 665