Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3548 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7239. Min Range: -0.7239

Max Act: 0.7239. Min Act: -0.0001

Data Index: 661048 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 0.7239. Min Range: -0.7239

Max Act: 0.6898. Min Act: -0.0001

Data Index: 722190 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 0.7239. Min Range: -0.7239

Max Act: 0.6838. Min Act: -0.0001

Data Index: 581774 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.7239. Min Range: -0.7239

Max Act: 0.6504. Min Act: -0.0001

Data Index: 1036969 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 0.7239. Min Range: -0.7239

Max Act: 0.5856. Min Act: -0.0000

Data Index: 131900 (C4 (Web Text))

Max Activating Token Index: 223

Text #5

Max Range: 0.7239. Min Range: -0.7239

Max Act: 0.5412. Min Act: -0.0000

Data Index: 1323166 (C4 (Web Text))

Max Activating Token Index: 212

Text #6

Max Range: 0.7239. Min Range: -0.7239

Max Act: 0.5230. Min Act: -0.0001

Data Index: 344715 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 0.7239. Min Range: -0.7239

Max Act: 0.5380. Min Act: -0.0001

Data Index: 1033917 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 0.7239. Min Range: -0.7239

Max Act: 0.5166. Min Act: -0.0001

Data Index: 548871 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 0.7239. Min Range: -0.7239

Max Act: 0.4978. Min Act: -0.0001

Data Index: 1137183 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 0.7239. Min Range: -0.7239

Max Act: 0.5091. Min Act: -0.0000

Data Index: 964804 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 0.7239. Min Range: -0.7239

Max Act: 0.5018. Min Act: -0.0000

Data Index: 1150094 (C4 (Web Text))

Max Activating Token Index: 774

Text #12

Max Range: 0.7239. Min Range: -0.7239

Max Act: 0.4997. Min Act: -0.0001

Data Index: 1017298 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 0.7239. Min Range: -0.7239

Max Act: 0.4727. Min Act: -0.0000

Data Index: 419080 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 0.7239. Min Range: -0.7239

Max Act: 0.4549. Min Act: -0.0000

Data Index: 298916 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 0.7239. Min Range: -0.7239

Max Act: 0.4454. Min Act: -0.0001

Data Index: 1257109 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 0.7239. Min Range: -0.7239

Max Act: 0.4252. Min Act: -0.0000

Data Index: 729148 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 0.7239. Min Range: -0.7239

Max Act: 0.4467. Min Act: -0.0000

Data Index: 479919 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 0.7239. Min Range: -0.7239

Max Act: 0.4213. Min Act: -0.0001

Data Index: 859375 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 0.7239. Min Range: -0.7239

Max Act: 0.4359. Min Act: -0.0000

Data Index: 892134 (C4 (Web Text))

Max Activating Token Index: 697