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

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

Neuron 1100 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0202. Min Act: -0.0002

Data Index: 114308 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0193. Min Act: -0.0003

Data Index: 970102 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0189. Min Act: -0.0002

Data Index: 1138945 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0189. Min Act: -0.0003

Data Index: 925996 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0188. Min Act: -0.0003

Data Index: 655303 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0184. Min Act: -0.0003

Data Index: 376380 (C4 (Web Text))

Max Activating Token Index: 643

Text #6

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0189. Min Act: -0.0003

Data Index: 1033077 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0176. Min Act: -0.0003

Data Index: 948942 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0175. Min Act: -0.0003

Data Index: 53426 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0165. Min Act: -0.0003

Data Index: 1257904 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0170. Min Act: -0.0002

Data Index: 646202 (C4 (Web Text))

Max Activating Token Index: 491

Text #11

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0168. Min Act: -0.0003

Data Index: 97133 (C4 (Web Text))

Max Activating Token Index: 533

Text #12

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0165. Min Act: -0.0003

Data Index: 581444 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0159. Min Act: -0.0002

Data Index: 289076 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0169. Min Act: -0.0003

Data Index: 337579 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0165. Min Act: -0.0003

Data Index: 411265 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0166. Min Act: -0.0003

Data Index: 1188677 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0161. Min Act: -0.0003

Data Index: 775218 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0155. Min Act: -0.0002

Data Index: 62830 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0152. Min Act: -0.0003

Data Index: 1223055 (C4 (Web Text))

Max Activating Token Index: 615