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

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

Neuron 3660 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1535. Min Act: -0.0002

Data Index: 63165 (C4 (Web Text))

Max Activating Token Index: 370

Text #1

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1371. Min Act: -0.0003

Data Index: 785155 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1407. Min Act: -0.0003

Data Index: 792732 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1359. Min Act: -0.0002

Data Index: 1094235 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1283. Min Act: -0.0003

Data Index: 101648 (C4 (Web Text))

Max Activating Token Index: 161

Text #5

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1337. Min Act: -0.0002

Data Index: 914264 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1328. Min Act: -0.0003

Data Index: 1197206 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1276. Min Act: -0.0003

Data Index: 246668 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1228. Min Act: -0.0003

Data Index: 126697 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1304. Min Act: -0.0002

Data Index: 231214 (C4 (Web Text))

Max Activating Token Index: 219

Text #10

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1250. Min Act: -0.0003

Data Index: 393085 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1248. Min Act: -0.0003

Data Index: 1154108 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1186. Min Act: -0.0003

Data Index: 635284 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1243. Min Act: -0.0003

Data Index: 950180 (C4 (Web Text))

Max Activating Token Index: 235

Text #14

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1233. Min Act: -0.0003

Data Index: 68410 (C4 (Web Text))

Max Activating Token Index: 337

Text #15

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1230. Min Act: -0.0002

Data Index: 784838 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1225. Min Act: -0.0003

Data Index: 169338 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1215. Min Act: -0.0003

Data Index: 411695 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1170. Min Act: -0.0003

Data Index: 251389 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 0.1535. Min Range: -0.1535

Max Act: 0.1208. Min Act: -0.0003

Data Index: 1324711 (C4 (Web Text))

Max Activating Token Index: 24