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

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

Neuron 3609 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1184. Min Range: -5.1184

Max Act: 5.1184. Min Act: -0.0000

Data Index: 263833 (C4 (Web Text))

Max Activating Token Index: 154

Text #1

Max Range: 5.1184. Min Range: -5.1184

Max Act: 4.8154. Min Act: -0.0000

Data Index: 936476 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 5.1184. Min Range: -5.1184

Max Act: 4.4447. Min Act: -0.0000

Data Index: 496198 (C4 (Web Text))

Max Activating Token Index: 1017

Text #3

Max Range: 5.1184. Min Range: -5.1184

Max Act: 4.4006. Min Act: -0.0000

Data Index: 617930 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 5.1184. Min Range: -5.1184

Max Act: 4.3170. Min Act: -0.0000

Data Index: 1023969 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 5.1184. Min Range: -5.1184

Max Act: 4.5115. Min Act: -0.0000

Data Index: 436497 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 5.1184. Min Range: -5.1184

Max Act: 4.5291. Min Act: -0.0000

Data Index: 1043396 (C4 (Web Text))

Max Activating Token Index: 975

Text #7

Max Range: 5.1184. Min Range: -5.1184

Max Act: 4.1308. Min Act: -0.0000

Data Index: 334937 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 5.1184. Min Range: -5.1184

Max Act: 4.4726. Min Act: -0.0000

Data Index: 1326070 (C4 (Web Text))

Max Activating Token Index: 708

Text #9

Max Range: 5.1184. Min Range: -5.1184

Max Act: 4.2325. Min Act: -0.0000

Data Index: 127079 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 5.1184. Min Range: -5.1184

Max Act: 4.4069. Min Act: -0.0000

Data Index: 112954 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 5.1184. Min Range: -5.1184

Max Act: 4.0478. Min Act: -0.0000

Data Index: 476660 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 5.1184. Min Range: -5.1184

Max Act: 4.2219. Min Act: -0.0000

Data Index: 270860 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 5.1184. Min Range: -5.1184

Max Act: 4.2157. Min Act: -0.0000

Data Index: 1307012 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 5.1184. Min Range: -5.1184

Max Act: 4.5199. Min Act: -0.0000

Data Index: 1016067 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 5.1184. Min Range: -5.1184

Max Act: 4.0200. Min Act: -0.0000

Data Index: 291707 (C4 (Web Text))

Max Activating Token Index: 566

Text #16

Max Range: 5.1184. Min Range: -5.1184

Max Act: 4.1926. Min Act: -0.0000

Data Index: 597151 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 5.1184. Min Range: -5.1184

Max Act: 4.1385. Min Act: -0.0000

Data Index: 890786 (C4 (Web Text))

Max Activating Token Index: 912

Text #18

Max Range: 5.1184. Min Range: -5.1184

Max Act: 4.1813. Min Act: -0.0000

Data Index: 1022025 (C4 (Web Text))

Max Activating Token Index: 238

Text #19

Max Range: 5.1184. Min Range: -5.1184

Max Act: 4.1269. Min Act: -0.0000

Data Index: 455971 (C4 (Web Text))

Max Activating Token Index: 392