Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3203 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.8128. Min Act: -0.0000

Data Index: 142256 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.7182. Min Act: -0.0000

Data Index: 866597 (C4 (Web Text))

Max Activating Token Index: 451

Text #2

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.6410. Min Act: -0.0000

Data Index: 602715 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.6223. Min Act: -0.0000

Data Index: 187337 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.6903. Min Act: -0.0000

Data Index: 460420 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.6636. Min Act: -0.0000

Data Index: 519999 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.5845. Min Act: 0.0000

Data Index: 452876 (C4 (Web Text))

Max Activating Token Index: 649

Text #7

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.5892. Min Act: -0.0000

Data Index: 1137103 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.5978. Min Act: -0.0000

Data Index: 782587 (C4 (Web Text))

Max Activating Token Index: 465

Text #9

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.6011. Min Act: -0.0000

Data Index: 279791 (C4 (Web Text))

Max Activating Token Index: 676

Text #10

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.5881. Min Act: 0.0000

Data Index: 65318 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.5730. Min Act: -0.0000

Data Index: 551972 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.5304. Min Act: -0.0000

Data Index: 935000 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.5176. Min Act: -0.0000

Data Index: 790848 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.5415. Min Act: -0.0000

Data Index: 74559 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.5285. Min Act: -0.0000

Data Index: 1247021 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.4957. Min Act: -0.0000

Data Index: 215897 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.4922. Min Act: -0.0000

Data Index: 1241311 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.4839. Min Act: -0.0000

Data Index: 816978 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.4917. Min Act: -0.0000

Data Index: 826484 (C4 (Web Text))

Max Activating Token Index: 610