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

Dataset: Open Web Text

Neuron 1292 in Layer 0

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: 5.6188. Min Range: -5.6188

Max Act: 5.6188. Min Act: -0.1700

Data Index: 6951503 (Open Web Text)

Max Activating Token Index: 545

Text #1

Max Range: 5.6188. Min Range: -5.6188

Max Act: 4.8666. Min Act: -0.1700

Data Index: 1655532 (Open Web Text)

Max Activating Token Index: 700

Text #2

Max Range: 5.6188. Min Range: -5.6188

Max Act: 4.8210. Min Act: -0.1700

Data Index: 5952273 (Open Web Text)

Max Activating Token Index: 556

Text #3

Max Range: 5.6188. Min Range: -5.6188

Max Act: 4.8241. Min Act: -0.1700

Data Index: 6979103 (Open Web Text)

Max Activating Token Index: 496

Text #4

Max Range: 5.6188. Min Range: -5.6188

Max Act: 4.7920. Min Act: -0.1700

Data Index: 5669437 (Open Web Text)

Max Activating Token Index: 844

Text #5

Max Range: 5.6188. Min Range: -5.6188

Max Act: 4.7633. Min Act: -0.1700

Data Index: 3187991 (Open Web Text)

Max Activating Token Index: 308

Text #6

Max Range: 5.6188. Min Range: -5.6188

Max Act: 4.7593. Min Act: -0.1700

Data Index: 6590882 (Open Web Text)

Max Activating Token Index: 771

Text #7

Max Range: 5.6188. Min Range: -5.6188

Max Act: 4.7480. Min Act: -0.1700

Data Index: 864012 (Open Web Text)

Max Activating Token Index: 770

Text #8

Max Range: 5.6188. Min Range: -5.6188

Max Act: 4.6898. Min Act: -0.1700

Data Index: 7022820 (Open Web Text)

Max Activating Token Index: 786

Text #9

Max Range: 5.6188. Min Range: -5.6188

Max Act: 4.6687. Min Act: -0.1700

Data Index: 1984636 (Open Web Text)

Max Activating Token Index: 794

Text #10

Max Range: 5.6188. Min Range: -5.6188

Max Act: 4.6593. Min Act: -0.1700

Data Index: 5669436 (Open Web Text)

Max Activating Token Index: 1009

Text #11

Max Range: 5.6188. Min Range: -5.6188

Max Act: 4.6437. Min Act: -0.1700

Data Index: 928281 (Open Web Text)

Max Activating Token Index: 463

Text #12

Max Range: 5.6188. Min Range: -5.6188

Max Act: 4.6382. Min Act: -0.1700

Data Index: 2920049 (Open Web Text)

Max Activating Token Index: 277

Text #13

Max Range: 5.6188. Min Range: -5.6188

Max Act: 4.6372. Min Act: -0.1700

Data Index: 954863 (Open Web Text)

Max Activating Token Index: 691

Text #14

Max Range: 5.6188. Min Range: -5.6188

Max Act: 4.6233. Min Act: -0.1700

Data Index: 8031477 (Open Web Text)

Max Activating Token Index: 727

Text #15

Max Range: 5.6188. Min Range: -5.6188

Max Act: 4.5944. Min Act: -0.1700

Data Index: 5509461 (Open Web Text)

Max Activating Token Index: 1022

Text #16

Max Range: 5.6188. Min Range: -5.6188

Max Act: 4.6006. Min Act: -0.1700

Data Index: 7776727 (Open Web Text)

Max Activating Token Index: 636

Text #17

Max Range: 5.6188. Min Range: -5.6188

Max Act: 4.5932. Min Act: -0.1700

Data Index: 5559832 (Open Web Text)

Max Activating Token Index: 989

Text #18

Max Range: 5.6188. Min Range: -5.6188

Max Act: 4.6048. Min Act: -0.1700

Data Index: 4798077 (Open Web Text)

Max Activating Token Index: 980

Text #19

Max Range: 5.6188. Min Range: -5.6188

Max Act: 4.5787. Min Act: -0.1700

Data Index: 3032557 (Open Web Text)

Max Activating Token Index: 571