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

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

Neuron 2405 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3754. Min Range: -1.3754

Max Act: 1.3654. Min Act: -0.0001

Data Index: 614420 (C4 (Web Text))

Max Activating Token Index: 1011

Text #1

Max Range: 1.3754. Min Range: -1.3754

Max Act: 1.2489. Min Act: -0.0001

Data Index: 731526 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 1.3754. Min Range: -1.3754

Max Act: 1.2459. Min Act: -0.0001

Data Index: 575672 (C4 (Web Text))

Max Activating Token Index: 511

Text #3

Max Range: 1.3754. Min Range: -1.3754

Max Act: 1.2019. Min Act: -0.0001

Data Index: 1064830 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 1.3754. Min Range: -1.3754

Max Act: 1.3754. Min Act: -0.0001

Data Index: 695543 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 1.3754. Min Range: -1.3754

Max Act: 1.2043. Min Act: -0.0001

Data Index: 671750 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 1.3754. Min Range: -1.3754

Max Act: 1.2657. Min Act: -0.0001

Data Index: 371283 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 1.3754. Min Range: -1.3754

Max Act: 1.1383. Min Act: -0.0001

Data Index: 619924 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 1.3754. Min Range: -1.3754

Max Act: 1.2630. Min Act: -0.0001

Data Index: 285752 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 1.3754. Min Range: -1.3754

Max Act: 1.2358. Min Act: -0.0001

Data Index: 1236086 (C4 (Web Text))

Max Activating Token Index: 531

Text #10

Max Range: 1.3754. Min Range: -1.3754

Max Act: 1.2381. Min Act: -0.0001

Data Index: 822393 (C4 (Web Text))

Max Activating Token Index: 64

Text #11

Max Range: 1.3754. Min Range: -1.3754

Max Act: 1.2207. Min Act: -0.0001

Data Index: 663307 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 1.3754. Min Range: -1.3754

Max Act: 1.0770. Min Act: -0.0001

Data Index: 1303528 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 1.3754. Min Range: -1.3754

Max Act: 1.1557. Min Act: -0.0001

Data Index: 116250 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 1.3754. Min Range: -1.3754

Max Act: 1.1381. Min Act: -0.0001

Data Index: 851407 (C4 (Web Text))

Max Activating Token Index: 934

Text #15

Max Range: 1.3754. Min Range: -1.3754

Max Act: 1.1739. Min Act: -0.0001

Data Index: 652782 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 1.3754. Min Range: -1.3754

Max Act: 1.1847. Min Act: -0.0001

Data Index: 317359 (C4 (Web Text))

Max Activating Token Index: 1015

Text #17

Max Range: 1.3754. Min Range: -1.3754

Max Act: 1.1098. Min Act: -0.0001

Data Index: 564526 (C4 (Web Text))

Max Activating Token Index: 415

Text #18

Max Range: 1.3754. Min Range: -1.3754

Max Act: 1.1513. Min Act: -0.0001

Data Index: 736851 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 1.3754. Min Range: -1.3754

Max Act: 1.1549. Min Act: -0.0001

Data Index: 1260185 (C4 (Web Text))

Max Activating Token Index: 320