Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 20 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0301. Min Act: -0.0005

Data Index: 514263 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0278. Min Act: -0.0005

Data Index: 704134 (C4 (Web Text))

Max Activating Token Index: 568

Text #2

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0295. Min Act: -0.0005

Data Index: 124345 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0282. Min Act: -0.0005

Data Index: 1162542 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0266. Min Act: -0.0005

Data Index: 1339410 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0255. Min Act: -0.0005

Data Index: 341506 (C4 (Web Text))

Max Activating Token Index: 252

Text #6

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0252. Min Act: -0.0005

Data Index: 303969 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0252. Min Act: -0.0005

Data Index: 106766 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0256. Min Act: -0.0005

Data Index: 1057211 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0254. Min Act: -0.0005

Data Index: 813142 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0256. Min Act: -0.0005

Data Index: 424932 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0262. Min Act: -0.0004

Data Index: 817919 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0244. Min Act: -0.0005

Data Index: 1077446 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0255. Min Act: -0.0005

Data Index: 605850 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0252. Min Act: -0.0005

Data Index: 45242 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0251. Min Act: -0.0005

Data Index: 1137133 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0244. Min Act: -0.0004

Data Index: 280054 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0249. Min Act: -0.0005

Data Index: 1265214 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0241. Min Act: -0.0005

Data Index: 677350 (C4 (Web Text))

Max Activating Token Index: 674

Text #19

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0229. Min Act: -0.0005

Data Index: 292252 (C4 (Web Text))

Max Activating Token Index: 592