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

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

Neuron 1512 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0296. Min Act: -0.0002

Data Index: 489263 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0284. Min Act: -0.0002

Data Index: 321950 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0283. Min Act: -0.0002

Data Index: 1071223 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0261. Min Act: -0.0002

Data Index: 69352 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0241. Min Act: -0.0002

Data Index: 594399 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0239. Min Act: -0.0002

Data Index: 178613 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0226. Min Act: -0.0002

Data Index: 818027 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0224. Min Act: -0.0002

Data Index: 221611 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0217. Min Act: -0.0002

Data Index: 106785 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0215. Min Act: -0.0002

Data Index: 801905 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0216. Min Act: -0.0002

Data Index: 390656 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0218. Min Act: -0.0002

Data Index: 1395990 (Python Code)

Max Activating Token Index: 834

Text #12

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0209. Min Act: -0.0002

Data Index: 816065 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0205. Min Act: -0.0002

Data Index: 78893 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0202. Min Act: -0.0002

Data Index: 505748 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0202. Min Act: -0.0002

Data Index: 1589855 (Python Code)

Max Activating Token Index: 567

Text #16

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0185. Min Act: -0.0002

Data Index: 1043595 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0184. Min Act: -0.0002

Data Index: 521447 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0178. Min Act: -0.0002

Data Index: 783081 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0176. Min Act: -0.0002

Data Index: 290558 (C4 (Web Text))

Max Activating Token Index: 471