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

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

Neuron 1768 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.5167. Min Act: -0.0002

Data Index: 455880 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.4780. Min Act: -0.0002

Data Index: 1248493 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.4224. Min Act: -0.0002

Data Index: 1009643 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.4289. Min Act: -0.0003

Data Index: 283865 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3960. Min Act: -0.0003

Data Index: 933213 (C4 (Web Text))

Max Activating Token Index: 793

Text #5

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3894. Min Act: -0.0002

Data Index: 848482 (C4 (Web Text))

Max Activating Token Index: 440

Text #6

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3737. Min Act: -0.0002

Data Index: 829554 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3729. Min Act: -0.0003

Data Index: 1064584 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3731. Min Act: -0.0002

Data Index: 1219875 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3687. Min Act: -0.0003

Data Index: 660002 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3694. Min Act: -0.0002

Data Index: 469069 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3655. Min Act: -0.0003

Data Index: 1241920 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3690. Min Act: -0.0003

Data Index: 634668 (C4 (Web Text))

Max Activating Token Index: 248

Text #13

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3743. Min Act: -0.0003

Data Index: 1154270 (C4 (Web Text))

Max Activating Token Index: 674

Text #14

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3525. Min Act: -0.0002

Data Index: 503248 (C4 (Web Text))

Max Activating Token Index: 455

Text #15

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3623. Min Act: -0.0003

Data Index: 497329 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3479. Min Act: -0.0002

Data Index: 1018584 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3583. Min Act: -0.0003

Data Index: 1298853 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3594. Min Act: -0.0003

Data Index: 1065911 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 0.5167. Min Range: -0.5167

Max Act: 0.3565. Min Act: -0.0002

Data Index: 398427 (C4 (Web Text))

Max Activating Token Index: 183