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

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

Neuron 4171 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0296. Min Act: -0.0002

Data Index: 1263543 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0271. Min Act: -0.0002

Data Index: 1045493 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0237. Min Act: -0.0002

Data Index: 541608 (C4 (Web Text))

Max Activating Token Index: 415

Text #3

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0229. Min Act: -0.0002

Data Index: 19274 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0227. Min Act: -0.0002

Data Index: 789723 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0208. Min Act: -0.0002

Data Index: 361617 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0213. Min Act: -0.0002

Data Index: 908124 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0228. Min Act: -0.0002

Data Index: 1349531 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0215. Min Act: -0.0002

Data Index: 106862 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0220. Min Act: -0.0002

Data Index: 309811 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0213. Min Act: -0.0002

Data Index: 1012271 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0206. Min Act: -0.0002

Data Index: 1330354 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0207. Min Act: -0.0002

Data Index: 196664 (C4 (Web Text))

Max Activating Token Index: 436

Text #13

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0203. Min Act: -0.0002

Data Index: 863100 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0200. Min Act: -0.0002

Data Index: 791012 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0204. Min Act: -0.0002

Data Index: 649729 (C4 (Web Text))

Max Activating Token Index: 124

Text #16

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0210. Min Act: -0.0002

Data Index: 668274 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0192. Min Act: -0.0002

Data Index: 628429 (C4 (Web Text))

Max Activating Token Index: 755

Text #18

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0203. Min Act: -0.0002

Data Index: 906113 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0206. Min Act: -0.0002

Data Index: 18075 (C4 (Web Text))

Max Activating Token Index: 957