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

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

Neuron 3578 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0269. Min Act: -0.0002

Data Index: 909127 (C4 (Web Text))

Max Activating Token Index: 577

Text #1

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0243. Min Act: -0.0002

Data Index: 707587 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0189. Min Act: -0.0001

Data Index: 193630 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0177. Min Act: -0.0002

Data Index: 223071 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0179. Min Act: -0.0001

Data Index: 349039 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0196. Min Act: -0.0001

Data Index: 640167 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0186. Min Act: -0.0002

Data Index: 219708 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0175. Min Act: -0.0002

Data Index: 96124 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0173. Min Act: -0.0001

Data Index: 1505370 (Python Code)

Max Activating Token Index: 35

Text #9

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0166. Min Act: -0.0001

Data Index: 1302410 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0187. Min Act: -0.0001

Data Index: 26254 (C4 (Web Text))

Max Activating Token Index: 815

Text #11

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0164. Min Act: -0.0002

Data Index: 342023 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0163. Min Act: -0.0001

Data Index: 1467128 (Python Code)

Max Activating Token Index: 38

Text #13

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0129. Min Act: -0.0001

Data Index: 1600269 (Python Code)

Max Activating Token Index: 410

Text #14

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0151. Min Act: -0.0001

Data Index: 968288 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0158. Min Act: -0.0001

Data Index: 740782 (C4 (Web Text))

Max Activating Token Index: 586

Text #16

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0166. Min Act: -0.0002

Data Index: 1281068 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0155. Min Act: -0.0001

Data Index: 815228 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0158. Min Act: -0.0002

Data Index: 585785 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 0.0269. Min Range: -0.0269

Max Act: 0.0160. Min Act: -0.0001

Data Index: 186938 (C4 (Web Text))

Max Activating Token Index: 584