Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4972 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1095. Min Range: -2.1095

Max Act: 2.1095. Min Act: -0.0000

Data Index: 511791 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.4193. Min Act: -0.0000

Data Index: 453320 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.9376. Min Act: -0.0000

Data Index: 276362 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.8989. Min Act: -0.0000

Data Index: 842542 (C4 (Web Text))

Max Activating Token Index: 728

Text #4

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.8627. Min Act: -0.0000

Data Index: 762346 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.7252. Min Act: -0.0000

Data Index: 1261004 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.9360. Min Act: -0.0000

Data Index: 1271053 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.6720. Min Act: -0.0000

Data Index: 987808 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.6600. Min Act: -0.0000

Data Index: 652517 (C4 (Web Text))

Max Activating Token Index: 501

Text #9

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.6161. Min Act: -0.0000

Data Index: 997233 (C4 (Web Text))

Max Activating Token Index: 370

Text #10

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.7002. Min Act: -0.0000

Data Index: 334878 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.6655. Min Act: -0.0000

Data Index: 752329 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.7484. Min Act: -0.0000

Data Index: 14395 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.6134. Min Act: -0.0000

Data Index: 28519 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.5513. Min Act: -0.0000

Data Index: 656755 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.6370. Min Act: -0.0000

Data Index: 1076186 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.5367. Min Act: -0.0000

Data Index: 1105662 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.5880. Min Act: -0.0000

Data Index: 198362 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.3344. Min Act: -0.0000

Data Index: 301864 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 2.1095. Min Range: -2.1095

Max Act: 1.5887. Min Act: -0.0000

Data Index: 1037974 (C4 (Web Text))

Max Activating Token Index: 348