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

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

Neuron 3982 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: 5.2851. Min Range: -5.2851

Max Act: 5.2851. Min Act: -0.0000

Data Index: 484972 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 5.2851. Min Range: -5.2851

Max Act: 4.3849. Min Act: -0.0000

Data Index: 717946 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 5.2851. Min Range: -5.2851

Max Act: 4.5129. Min Act: -0.0000

Data Index: 31341 (C4 (Web Text))

Max Activating Token Index: 405

Text #3

Max Range: 5.2851. Min Range: -5.2851

Max Act: 4.3359. Min Act: -0.0000

Data Index: 766016 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 5.2851. Min Range: -5.2851

Max Act: 4.4887. Min Act: -0.0000

Data Index: 430957 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 5.2851. Min Range: -5.2851

Max Act: 4.2394. Min Act: -0.0000

Data Index: 136117 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 5.2851. Min Range: -5.2851

Max Act: 4.2042. Min Act: -0.0000

Data Index: 296263 (C4 (Web Text))

Max Activating Token Index: 131

Text #7

Max Range: 5.2851. Min Range: -5.2851

Max Act: 4.1563. Min Act: -0.0000

Data Index: 969790 (C4 (Web Text))

Max Activating Token Index: 771

Text #8

Max Range: 5.2851. Min Range: -5.2851

Max Act: 4.1321. Min Act: -0.0000

Data Index: 608372 (C4 (Web Text))

Max Activating Token Index: 262

Text #9

Max Range: 5.2851. Min Range: -5.2851

Max Act: 3.7109. Min Act: -0.0000

Data Index: 1188708 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 5.2851. Min Range: -5.2851

Max Act: 4.0857. Min Act: -0.0000

Data Index: 1206528 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 5.2851. Min Range: -5.2851

Max Act: 4.0294. Min Act: -0.0000

Data Index: 1027728 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 5.2851. Min Range: -5.2851

Max Act: 3.8838. Min Act: -0.0000

Data Index: 350683 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 5.2851. Min Range: -5.2851

Max Act: 3.8513. Min Act: -0.0000

Data Index: 611063 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 5.2851. Min Range: -5.2851

Max Act: 3.7044. Min Act: -0.0000

Data Index: 1133154 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 5.2851. Min Range: -5.2851

Max Act: 3.8169. Min Act: -0.0000

Data Index: 979607 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 5.2851. Min Range: -5.2851

Max Act: 3.5837. Min Act: -0.0000

Data Index: 386593 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 5.2851. Min Range: -5.2851

Max Act: 3.6143. Min Act: -0.0000

Data Index: 813145 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 5.2851. Min Range: -5.2851

Max Act: 3.5838. Min Act: -0.0000

Data Index: 40545 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 5.2851. Min Range: -5.2851

Max Act: 3.5482. Min Act: -0.0000

Data Index: 1283868 (C4 (Web Text))

Max Activating Token Index: 1019