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

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

Neuron 862 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0306. Min Act: -0.0000

Data Index: 486817 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0309. Min Act: -0.0000

Data Index: 924934 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0297. Min Act: -0.0000

Data Index: 1516072 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0247. Min Act: -0.0000

Data Index: 442867 (C4 (Web Text))

Max Activating Token Index: 468

Text #4

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0240. Min Act: -0.0000

Data Index: 1284959 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0239. Min Act: -0.0000

Data Index: 919804 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0208. Min Act: -0.0000

Data Index: 688480 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0175. Min Act: -0.0000

Data Index: 86092 (C4 (Web Text))

Max Activating Token Index: 711

Text #8

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0202. Min Act: -0.0000

Data Index: 462896 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0198. Min Act: -0.0000

Data Index: 974689 (C4 (Web Text))

Max Activating Token Index: 447

Text #10

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0200. Min Act: -0.0000

Data Index: 386932 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0195. Min Act: -0.0000

Data Index: 97902 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0210. Min Act: -0.0000

Data Index: 109761 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0186. Min Act: -0.0000

Data Index: 1335157 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0184. Min Act: -0.0000

Data Index: 1628376 (Python Code)

Max Activating Token Index: 227

Text #15

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0201. Min Act: -0.0000

Data Index: 1048215 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0194. Min Act: -0.0000

Data Index: 1223363 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0189. Min Act: -0.0000

Data Index: 606970 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0192. Min Act: -0.0000

Data Index: 949423 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0174. Min Act: -0.0000

Data Index: 1099979 (C4 (Web Text))

Max Activating Token Index: 387