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

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

Neuron 537 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: 0.0041. Min Range: -0.0041

Max Act: 0.0041. Min Act: -0.0005

Data Index: 171942 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0038. Min Act: -0.0005

Data Index: 184685 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0037. Min Act: -0.0005

Data Index: 1611543 (Python Code)

Max Activating Token Index: 190

Text #3

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0035. Min Act: -0.0005

Data Index: 527172 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0035. Min Act: -0.0005

Data Index: 1606528 (Python Code)

Max Activating Token Index: 173

Text #5

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0034. Min Act: -0.0005

Data Index: 100002 (C4 (Web Text))

Max Activating Token Index: 196

Text #6

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0033. Min Act: -0.0006

Data Index: 54886 (C4 (Web Text))

Max Activating Token Index: 272

Text #7

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0033. Min Act: -0.0005

Data Index: 699188 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0033. Min Act: -0.0005

Data Index: 74562 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0031. Min Act: -0.0005

Data Index: 1175986 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0031. Min Act: -0.0006

Data Index: 1391259 (Python Code)

Max Activating Token Index: 204

Text #11

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0030. Min Act: -0.0005

Data Index: 166853 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0030. Min Act: -0.0005

Data Index: 1302060 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0030. Min Act: -0.0005

Data Index: 574855 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0029. Min Act: -0.0005

Data Index: 586656 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0029. Min Act: -0.0005

Data Index: 1300368 (C4 (Web Text))

Max Activating Token Index: 9

Text #16

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0030. Min Act: -0.0005

Data Index: 358865 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0029. Min Act: -0.0005

Data Index: 1193321 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0029. Min Act: -0.0005

Data Index: 622015 (C4 (Web Text))

Max Activating Token Index: 163

Text #19

Max Range: 0.0041. Min Range: -0.0041

Max Act: 0.0029. Min Act: -0.0005

Data Index: 73702 (C4 (Web Text))

Max Activating Token Index: 170