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

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

Neuron 2753 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6110. Min Range: -0.6110

Max Act: 0.6110. Min Act: -0.0000

Data Index: 193159 (C4 (Web Text))

Max Activating Token Index: 999

Text #1

Max Range: 0.6110. Min Range: -0.6110

Max Act: 0.5542. Min Act: -0.0000

Data Index: 1335922 (C4 (Web Text))

Max Activating Token Index: 628

Text #2

Max Range: 0.6110. Min Range: -0.6110

Max Act: 0.5406. Min Act: -0.0000

Data Index: 795335 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 0.6110. Min Range: -0.6110

Max Act: 0.4467. Min Act: -0.0000

Data Index: 1213656 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 0.6110. Min Range: -0.6110

Max Act: 0.4068. Min Act: -0.0000

Data Index: 417510 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 0.6110. Min Range: -0.6110

Max Act: 0.4051. Min Act: -0.0000

Data Index: 269992 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 0.6110. Min Range: -0.6110

Max Act: 0.4149. Min Act: -0.0000

Data Index: 994323 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 0.6110. Min Range: -0.6110

Max Act: 0.3867. Min Act: -0.0000

Data Index: 176717 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 0.6110. Min Range: -0.6110

Max Act: 0.3714. Min Act: -0.0000

Data Index: 735075 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 0.6110. Min Range: -0.6110

Max Act: 0.3737. Min Act: -0.0000

Data Index: 516275 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 0.6110. Min Range: -0.6110

Max Act: 0.3836. Min Act: -0.0000

Data Index: 959497 (C4 (Web Text))

Max Activating Token Index: 847

Text #11

Max Range: 0.6110. Min Range: -0.6110

Max Act: 0.3600. Min Act: -0.0000

Data Index: 1266926 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 0.6110. Min Range: -0.6110

Max Act: 0.3669. Min Act: -0.0000

Data Index: 1348593 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 0.6110. Min Range: -0.6110

Max Act: 0.3782. Min Act: -0.0000

Data Index: 1216406 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 0.6110. Min Range: -0.6110

Max Act: 0.3618. Min Act: -0.0000

Data Index: 1179480 (C4 (Web Text))

Max Activating Token Index: 721

Text #15

Max Range: 0.6110. Min Range: -0.6110

Max Act: 0.3441. Min Act: -0.0000

Data Index: 413838 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.6110. Min Range: -0.6110

Max Act: 0.3445. Min Act: -0.0000

Data Index: 970489 (C4 (Web Text))

Max Activating Token Index: 462

Text #17

Max Range: 0.6110. Min Range: -0.6110

Max Act: 0.3812. Min Act: -0.0000

Data Index: 316222 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 0.6110. Min Range: -0.6110

Max Act: 0.3576. Min Act: -0.0000

Data Index: 1290073 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 0.6110. Min Range: -0.6110

Max Act: 0.3774. Min Act: -0.0000

Data Index: 745324 (C4 (Web Text))

Max Activating Token Index: 214