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

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

Neuron 1225 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0261. Min Act: -0.0005

Data Index: 100290 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0223. Min Act: -0.0005

Data Index: 977101 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0209. Min Act: -0.0005

Data Index: 610658 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0207. Min Act: -0.0006

Data Index: 1072990 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0201. Min Act: -0.0005

Data Index: 714618 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0201. Min Act: -0.0005

Data Index: 247015 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0203. Min Act: -0.0005

Data Index: 1073945 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0192. Min Act: -0.0005

Data Index: 39052 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0192. Min Act: -0.0005

Data Index: 1534018 (Python Code)

Max Activating Token Index: 160

Text #9

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0186. Min Act: -0.0005

Data Index: 178138 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0193. Min Act: -0.0006

Data Index: 881727 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0188. Min Act: -0.0005

Data Index: 1266871 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0189. Min Act: -0.0005

Data Index: 1442044 (Python Code)

Max Activating Token Index: 288

Text #13

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0183. Min Act: -0.0005

Data Index: 893956 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0189. Min Act: -0.0006

Data Index: 1219070 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0187. Min Act: -0.0005

Data Index: 7092 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0184. Min Act: -0.0005

Data Index: 503618 (C4 (Web Text))

Max Activating Token Index: 273

Text #17

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0185. Min Act: -0.0005

Data Index: 971235 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0184. Min Act: -0.0005

Data Index: 587381 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0183. Min Act: -0.0005

Data Index: 818959 (C4 (Web Text))

Max Activating Token Index: 389