Model: GELU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 934 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.9130. Min Range: -3.9130

Max Act: 3.9130. Min Act: -0.1700

Data Index: 1309390 (C4 (Web Text))

Max Activating Token Index: 226

Text #1

Max Range: 3.9130. Min Range: -3.9130

Max Act: 3.8505. Min Act: -0.1700

Data Index: 278216 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 3.9130. Min Range: -3.9130

Max Act: 3.8505. Min Act: -0.1700

Data Index: 232477 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 3.9130. Min Range: -3.9130

Max Act: 3.8192. Min Act: -0.1700

Data Index: 1187430 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 3.9130. Min Range: -3.9130

Max Act: 3.8349. Min Act: -0.1700

Data Index: 264406 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 3.9130. Min Range: -3.9130

Max Act: 3.7879. Min Act: -0.1700

Data Index: 922386 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 3.9130. Min Range: -3.9130

Max Act: 3.8036. Min Act: -0.1700

Data Index: 870531 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 3.9130. Min Range: -3.9130

Max Act: 3.7879. Min Act: -0.1700

Data Index: 201113 (C4 (Web Text))

Max Activating Token Index: 887

Text #8

Max Range: 3.9130. Min Range: -3.9130

Max Act: 3.7410. Min Act: -0.1700

Data Index: 570150 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 3.9130. Min Range: -3.9130

Max Act: 3.7254. Min Act: -0.1700

Data Index: 56246 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 3.9130. Min Range: -3.9130

Max Act: 3.7097. Min Act: -0.1700

Data Index: 393770 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 3.9130. Min Range: -3.9130

Max Act: 3.7254. Min Act: -0.1700

Data Index: 976296 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 3.9130. Min Range: -3.9130

Max Act: 3.7254. Min Act: -0.1700

Data Index: 476617 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 3.9130. Min Range: -3.9130

Max Act: 3.7097. Min Act: -0.1700

Data Index: 260032 (C4 (Web Text))

Max Activating Token Index: 1016

Text #14

Max Range: 3.9130. Min Range: -3.9130

Max Act: 3.7097. Min Act: -0.1700

Data Index: 154077 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 3.9130. Min Range: -3.9130

Max Act: 3.7254. Min Act: -0.1700

Data Index: 604141 (C4 (Web Text))

Max Activating Token Index: 973

Text #16

Max Range: 3.9130. Min Range: -3.9130

Max Act: 3.7254. Min Act: -0.1700

Data Index: 177313 (C4 (Web Text))

Max Activating Token Index: 374

Text #17

Max Range: 3.9130. Min Range: -3.9130

Max Act: 3.6941. Min Act: -0.1700

Data Index: 531175 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 3.9130. Min Range: -3.9130

Max Act: 3.7097. Min Act: -0.1700

Data Index: 871901 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 3.9130. Min Range: -3.9130

Max Act: 3.7254. Min Act: -0.1700

Data Index: 685301 (C4 (Web Text))

Max Activating Token Index: 865