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

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

Neuron 1532 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.8152. Min Act: -0.0000

Data Index: 1251473 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.6929. Min Act: -0.0000

Data Index: 1015276 (C4 (Web Text))

Max Activating Token Index: 1011

Text #2

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.7698. Min Act: -0.0000

Data Index: 604272 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.6795. Min Act: -0.0000

Data Index: 181726 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.6649. Min Act: -0.0000

Data Index: 687718 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.7250. Min Act: -0.0000

Data Index: 216267 (C4 (Web Text))

Max Activating Token Index: 470

Text #6

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.5791. Min Act: -0.0000

Data Index: 1285372 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.6129. Min Act: -0.0000

Data Index: 693695 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.5343. Min Act: -0.0000

Data Index: 1190263 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.6267. Min Act: -0.0000

Data Index: 1152590 (C4 (Web Text))

Max Activating Token Index: 129

Text #10

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.6082. Min Act: -0.0000

Data Index: 944155 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.5940. Min Act: -0.0000

Data Index: 306551 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.5508. Min Act: -0.0000

Data Index: 673391 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.5368. Min Act: -0.0000

Data Index: 836612 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.4476. Min Act: -0.0000

Data Index: 567674 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.5153. Min Act: -0.0000

Data Index: 1233887 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.5039. Min Act: -0.0000

Data Index: 1293082 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.4944. Min Act: -0.0000

Data Index: 842422 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.4703. Min Act: -0.0000

Data Index: 99286 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.5494. Min Act: -0.0000

Data Index: 94734 (C4 (Web Text))

Max Activating Token Index: 582