Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6036 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4948. Min Range: -2.4948

Max Act: 2.4948. Min Act: -0.0000

Data Index: 553770 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 2.4948. Min Range: -2.4948

Max Act: 2.2214. Min Act: -0.0000

Data Index: 519941 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 2.4948. Min Range: -2.4948

Max Act: 2.0435. Min Act: -0.0000

Data Index: 1137031 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 2.4948. Min Range: -2.4948

Max Act: 1.9242. Min Act: -0.0000

Data Index: 1031637 (C4 (Web Text))

Max Activating Token Index: 1014

Text #4

Max Range: 2.4948. Min Range: -2.4948

Max Act: 1.8147. Min Act: -0.0000

Data Index: 1001697 (C4 (Web Text))

Max Activating Token Index: 511

Text #5

Max Range: 2.4948. Min Range: -2.4948

Max Act: 1.6972. Min Act: -0.0000

Data Index: 14106 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 2.4948. Min Range: -2.4948

Max Act: 1.6831. Min Act: -0.0000

Data Index: 1010406 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 2.4948. Min Range: -2.4948

Max Act: 1.7225. Min Act: -0.0000

Data Index: 363969 (C4 (Web Text))

Max Activating Token Index: 1002

Text #8

Max Range: 2.4948. Min Range: -2.4948

Max Act: 1.7199. Min Act: -0.0000

Data Index: 183656 (C4 (Web Text))

Max Activating Token Index: 1018

Text #9

Max Range: 2.4948. Min Range: -2.4948

Max Act: 1.5656. Min Act: -0.0000

Data Index: 97221 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 2.4948. Min Range: -2.4948

Max Act: 1.4425. Min Act: -0.0000

Data Index: 715253 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 2.4948. Min Range: -2.4948

Max Act: 1.4260. Min Act: -0.0000

Data Index: 400371 (C4 (Web Text))

Max Activating Token Index: 858

Text #12

Max Range: 2.4948. Min Range: -2.4948

Max Act: 1.5065. Min Act: -0.0000

Data Index: 1285986 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 2.4948. Min Range: -2.4948

Max Act: 1.5809. Min Act: -0.0000

Data Index: 951144 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 2.4948. Min Range: -2.4948

Max Act: 1.4929. Min Act: -0.0000

Data Index: 763336 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 2.4948. Min Range: -2.4948

Max Act: 1.4148. Min Act: -0.0000

Data Index: 535977 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 2.4948. Min Range: -2.4948

Max Act: 1.4778. Min Act: -0.0000

Data Index: 921650 (C4 (Web Text))

Max Activating Token Index: 960

Text #17

Max Range: 2.4948. Min Range: -2.4948

Max Act: 1.4471. Min Act: -0.0000

Data Index: 174821 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 2.4948. Min Range: -2.4948

Max Act: 1.5054. Min Act: -0.0000

Data Index: 73083 (C4 (Web Text))

Max Activating Token Index: 656

Text #19

Max Range: 2.4948. Min Range: -2.4948

Max Act: 1.4192. Min Act: -0.0000

Data Index: 839819 (C4 (Web Text))

Max Activating Token Index: 903