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

Dataset: Open Web Text

Neuron 1784 in Layer 5

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: 3.6333. Min Range: -3.6333

Max Act: 3.6333. Min Act: -0.1700

Data Index: 1691577 (Open Web Text)

Max Activating Token Index: 109

Text #1

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.6118. Min Act: -0.1700

Data Index: 3057381 (Open Web Text)

Max Activating Token Index: 346

Text #2

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.5941. Min Act: -0.1700

Data Index: 8323530 (Open Web Text)

Max Activating Token Index: 311

Text #3

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.5525. Min Act: -0.1700

Data Index: 4614875 (Open Web Text)

Max Activating Token Index: 147

Text #4

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.5607. Min Act: -0.1700

Data Index: 5332145 (Open Web Text)

Max Activating Token Index: 878

Text #5

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.5478. Min Act: -0.1700

Data Index: 359431 (Open Web Text)

Max Activating Token Index: 287

Text #6

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.5235. Min Act: -0.1700

Data Index: 1091282 (Open Web Text)

Max Activating Token Index: 327

Text #7

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.5398. Min Act: -0.1700

Data Index: 2188447 (Open Web Text)

Max Activating Token Index: 505

Text #8

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.5330. Min Act: -0.1700

Data Index: 6510440 (Open Web Text)

Max Activating Token Index: 805

Text #9

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.5339. Min Act: -0.1700

Data Index: 7954568 (Open Web Text)

Max Activating Token Index: 732

Text #10

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.5162. Min Act: -0.1700

Data Index: 5357439 (Open Web Text)

Max Activating Token Index: 394

Text #11

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.4879. Min Act: -0.1700

Data Index: 8685401 (Open Web Text)

Max Activating Token Index: 607

Text #12

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.5031. Min Act: -0.1700

Data Index: 7311651 (Open Web Text)

Max Activating Token Index: 731

Text #13

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.5050. Min Act: -0.1700

Data Index: 1210831 (Open Web Text)

Max Activating Token Index: 929

Text #14

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.4940. Min Act: -0.1700

Data Index: 8373007 (Open Web Text)

Max Activating Token Index: 903

Text #15

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.4959. Min Act: -0.1700

Data Index: 3099170 (Open Web Text)

Max Activating Token Index: 426

Text #16

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.4905. Min Act: -0.1700

Data Index: 6341952 (Open Web Text)

Max Activating Token Index: 396

Text #17

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.4791. Min Act: -0.1700

Data Index: 611042 (Open Web Text)

Max Activating Token Index: 151

Text #18

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.4721. Min Act: -0.1700

Data Index: 7114403 (Open Web Text)

Max Activating Token Index: 873

Text #19

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.4861. Min Act: -0.1700

Data Index: 1764200 (Open Web Text)

Max Activating Token Index: 221