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

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

Neuron 173 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8169. Min Range: -0.8169

Max Act: 0.8169. Min Act: -0.0006

Data Index: 221366 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 0.8169. Min Range: -0.8169

Max Act: 0.7905. Min Act: -0.0006

Data Index: 946995 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 0.8169. Min Range: -0.8169

Max Act: 0.7664. Min Act: -0.0006

Data Index: 1292988 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 0.8169. Min Range: -0.8169

Max Act: 0.6211. Min Act: -0.0006

Data Index: 970402 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 0.8169. Min Range: -0.8169

Max Act: 0.6617. Min Act: -0.0006

Data Index: 867690 (C4 (Web Text))

Max Activating Token Index: 293

Text #5

Max Range: 0.8169. Min Range: -0.8169

Max Act: 0.6755. Min Act: -0.0006

Data Index: 673700 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 0.8169. Min Range: -0.8169

Max Act: 0.6558. Min Act: -0.0006

Data Index: 913095 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 0.8169. Min Range: -0.8169

Max Act: 0.6543. Min Act: -0.0006

Data Index: 542326 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 0.8169. Min Range: -0.8169

Max Act: 0.6371. Min Act: -0.0006

Data Index: 357193 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 0.8169. Min Range: -0.8169

Max Act: 0.6164. Min Act: -0.0006

Data Index: 182473 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 0.8169. Min Range: -0.8169

Max Act: 0.6345. Min Act: -0.0006

Data Index: 1248507 (C4 (Web Text))

Max Activating Token Index: 271

Text #11

Max Range: 0.8169. Min Range: -0.8169

Max Act: 0.6315. Min Act: -0.0006

Data Index: 168209 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 0.8169. Min Range: -0.8169

Max Act: 0.6344. Min Act: -0.0006

Data Index: 173205 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 0.8169. Min Range: -0.8169

Max Act: 0.6345. Min Act: -0.0006

Data Index: 1215784 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 0.8169. Min Range: -0.8169

Max Act: 0.6118. Min Act: -0.0006

Data Index: 269443 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 0.8169. Min Range: -0.8169

Max Act: 0.6101. Min Act: -0.0006

Data Index: 503877 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 0.8169. Min Range: -0.8169

Max Act: 0.6292. Min Act: -0.0006

Data Index: 126015 (C4 (Web Text))

Max Activating Token Index: 7

Text #17

Max Range: 0.8169. Min Range: -0.8169

Max Act: 0.6259. Min Act: -0.0005

Data Index: 247191 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 0.8169. Min Range: -0.8169

Max Act: 0.6428. Min Act: -0.0006

Data Index: 1192093 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 0.8169. Min Range: -0.8169

Max Act: 0.6428. Min Act: -0.0006

Data Index: 1143678 (C4 (Web Text))

Max Activating Token Index: 51