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

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

Neuron 675 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0253. Min Act: -0.0001

Data Index: 948112 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0216. Min Act: -0.0001

Data Index: 104214 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0203. Min Act: -0.0001

Data Index: 1222996 (C4 (Web Text))

Max Activating Token Index: 293

Text #3

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0214. Min Act: -0.0001

Data Index: 399902 (C4 (Web Text))

Max Activating Token Index: 598

Text #4

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0205. Min Act: -0.0001

Data Index: 343199 (C4 (Web Text))

Max Activating Token Index: 302

Text #5

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0187. Min Act: -0.0001

Data Index: 1210925 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0219. Min Act: -0.0001

Data Index: 1100024 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0210. Min Act: -0.0001

Data Index: 267841 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0199. Min Act: -0.0001

Data Index: 1261744 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0187. Min Act: -0.0001

Data Index: 88292 (C4 (Web Text))

Max Activating Token Index: 312

Text #10

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0185. Min Act: -0.0001

Data Index: 1411338 (Python Code)

Max Activating Token Index: 811

Text #11

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0190. Min Act: -0.0001

Data Index: 1291616 (C4 (Web Text))

Max Activating Token Index: 456

Text #12

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0190. Min Act: -0.0001

Data Index: 1570040 (Python Code)

Max Activating Token Index: 68

Text #13

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0178. Min Act: -0.0001

Data Index: 341049 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0177. Min Act: -0.0001

Data Index: 248662 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0184. Min Act: -0.0001

Data Index: 215187 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0171. Min Act: -0.0001

Data Index: 608806 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0169. Min Act: -0.0001

Data Index: 1456409 (Python Code)

Max Activating Token Index: 592

Text #18

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0169. Min Act: -0.0001

Data Index: 1291636 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0175. Min Act: -0.0001

Data Index: 436991 (C4 (Web Text))

Max Activating Token Index: 372