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

Dataset: Open Web Text

Neuron 2006 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: 3.1367. Min Range: -3.1367

Max Act: 3.1367. Min Act: -0.1700

Data Index: 6645824 (Open Web Text)

Max Activating Token Index: 510

Text #1

Max Range: 3.1367. Min Range: -3.1367

Max Act: 3.1171. Min Act: -0.1700

Data Index: 7261227 (Open Web Text)

Max Activating Token Index: 534

Text #2

Max Range: 3.1367. Min Range: -3.1367

Max Act: 3.1073. Min Act: -0.1700

Data Index: 6210499 (Open Web Text)

Max Activating Token Index: 853

Text #3

Max Range: 3.1367. Min Range: -3.1367

Max Act: 3.1059. Min Act: -0.1700

Data Index: 8502737 (Open Web Text)

Max Activating Token Index: 575

Text #4

Max Range: 3.1367. Min Range: -3.1367

Max Act: 3.1100. Min Act: -0.1700

Data Index: 4606042 (Open Web Text)

Max Activating Token Index: 473

Text #5

Max Range: 3.1367. Min Range: -3.1367

Max Act: 3.0817. Min Act: -0.1700

Data Index: 1831002 (Open Web Text)

Max Activating Token Index: 182

Text #6

Max Range: 3.1367. Min Range: -3.1367

Max Act: 3.0688. Min Act: -0.1700

Data Index: 2475736 (Open Web Text)

Max Activating Token Index: 981

Text #7

Max Range: 3.1367. Min Range: -3.1367

Max Act: 3.1019. Min Act: -0.1700

Data Index: 3872091 (Open Web Text)

Max Activating Token Index: 436

Text #8

Max Range: 3.1367. Min Range: -3.1367

Max Act: 3.0901. Min Act: -0.1700

Data Index: 3673247 (Open Web Text)

Max Activating Token Index: 793

Text #9

Max Range: 3.1367. Min Range: -3.1367

Max Act: 3.0576. Min Act: -0.1700

Data Index: 243207 (Open Web Text)

Max Activating Token Index: 641

Text #10

Max Range: 3.1367. Min Range: -3.1367

Max Act: 3.0591. Min Act: -0.1700

Data Index: 7962826 (Open Web Text)

Max Activating Token Index: 369

Text #11

Max Range: 3.1367. Min Range: -3.1367

Max Act: 3.0472. Min Act: -0.1700

Data Index: 4557362 (Open Web Text)

Max Activating Token Index: 451

Text #12

Max Range: 3.1367. Min Range: -3.1367

Max Act: 3.0534. Min Act: -0.1700

Data Index: 8739050 (Open Web Text)

Max Activating Token Index: 754

Text #13

Max Range: 3.1367. Min Range: -3.1367

Max Act: 3.0345. Min Act: -0.1700

Data Index: 6714458 (Open Web Text)

Max Activating Token Index: 587

Text #14

Max Range: 3.1367. Min Range: -3.1367

Max Act: 3.0365. Min Act: -0.1700

Data Index: 6152960 (Open Web Text)

Max Activating Token Index: 657

Text #15

Max Range: 3.1367. Min Range: -3.1367

Max Act: 3.0342. Min Act: -0.1700

Data Index: 2392351 (Open Web Text)

Max Activating Token Index: 592

Text #16

Max Range: 3.1367. Min Range: -3.1367

Max Act: 3.0547. Min Act: -0.1700

Data Index: 606294 (Open Web Text)

Max Activating Token Index: 456

Text #17

Max Range: 3.1367. Min Range: -3.1367

Max Act: 3.0430. Min Act: -0.1700

Data Index: 3593864 (Open Web Text)

Max Activating Token Index: 535

Text #18

Max Range: 3.1367. Min Range: -3.1367

Max Act: 3.0219. Min Act: -0.1700

Data Index: 3317669 (Open Web Text)

Max Activating Token Index: 193

Text #19

Max Range: 3.1367. Min Range: -3.1367

Max Act: 3.0271. Min Act: -0.1700

Data Index: 4687992 (Open Web Text)

Max Activating Token Index: 220