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

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

Neuron 393 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: 0.4285. Min Range: -0.4285

Max Act: 0.4285. Min Act: -0.0001

Data Index: 819719 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.4165. Min Act: -0.0001

Data Index: 275341 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3552. Min Act: -0.0001

Data Index: 170064 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3784. Min Act: -0.0001

Data Index: 1208737 (C4 (Web Text))

Max Activating Token Index: 68

Text #4

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3861. Min Act: -0.0001

Data Index: 303047 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3701. Min Act: -0.0001

Data Index: 1210274 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3717. Min Act: -0.0001

Data Index: 1319492 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3628. Min Act: -0.0001

Data Index: 357778 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3538. Min Act: -0.0001

Data Index: 1336035 (C4 (Web Text))

Max Activating Token Index: 141

Text #9

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3412. Min Act: -0.0001

Data Index: 106132 (C4 (Web Text))

Max Activating Token Index: 76

Text #10

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3451. Min Act: -0.0001

Data Index: 14911 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3393. Min Act: -0.0001

Data Index: 1067940 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3351. Min Act: -0.0001

Data Index: 418585 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3236. Min Act: -0.0001

Data Index: 642110 (C4 (Web Text))

Max Activating Token Index: 159

Text #14

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3305. Min Act: -0.0001

Data Index: 1134796 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3307. Min Act: -0.0001

Data Index: 289466 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3216. Min Act: -0.0001

Data Index: 1156226 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3319. Min Act: -0.0001

Data Index: 1105222 (C4 (Web Text))

Max Activating Token Index: 224

Text #18

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3278. Min Act: -0.0001

Data Index: 512000 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 0.4285. Min Range: -0.4285

Max Act: 0.3191. Min Act: -0.0001

Data Index: 1049212 (C4 (Web Text))

Max Activating Token Index: 219