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

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

Neuron 4999 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1477. Min Act: -0.0001

Data Index: 164146 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1428. Min Act: -0.0001

Data Index: 5094 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1471. Min Act: -0.0001

Data Index: 1264585 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1319. Min Act: -0.0001

Data Index: 247637 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1237. Min Act: -0.0001

Data Index: 92522 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1337. Min Act: -0.0001

Data Index: 73126 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1275. Min Act: -0.0001

Data Index: 816373 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1180. Min Act: -0.0001

Data Index: 736762 (C4 (Web Text))

Max Activating Token Index: 634

Text #8

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1234. Min Act: -0.0001

Data Index: 159106 (C4 (Web Text))

Max Activating Token Index: 670

Text #9

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1052. Min Act: -0.0001

Data Index: 1249448 (C4 (Web Text))

Max Activating Token Index: 695

Text #10

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1152. Min Act: -0.0001

Data Index: 85365 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1113. Min Act: -0.0001

Data Index: 788645 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1192. Min Act: -0.0001

Data Index: 1308316 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1094. Min Act: -0.0001

Data Index: 438606 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1105. Min Act: -0.0001

Data Index: 825577 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1115. Min Act: -0.0001

Data Index: 1120941 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1214. Min Act: -0.0001

Data Index: 733252 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1070. Min Act: -0.0001

Data Index: 186857 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1184. Min Act: -0.0001

Data Index: 667654 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1132. Min Act: -0.0001

Data Index: 232286 (C4 (Web Text))

Max Activating Token Index: 275