Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2035 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7527. Min Range: -1.7527

Max Act: 1.7207. Min Act: -0.0001

Data Index: 120954 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 1.7527. Min Range: -1.7527

Max Act: 1.7041. Min Act: -0.0001

Data Index: 495072 (C4 (Web Text))

Max Activating Token Index: 622

Text #2

Max Range: 1.7527. Min Range: -1.7527

Max Act: 1.7527. Min Act: -0.0001

Data Index: 63574 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 1.7527. Min Range: -1.7527

Max Act: 1.4470. Min Act: -0.0001

Data Index: 686359 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 1.7527. Min Range: -1.7527

Max Act: 1.5165. Min Act: -0.0001

Data Index: 413645 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 1.7527. Min Range: -1.7527

Max Act: 1.4055. Min Act: -0.0001

Data Index: 858104 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 1.7527. Min Range: -1.7527

Max Act: 1.4941. Min Act: -0.0001

Data Index: 199416 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 1.7527. Min Range: -1.7527

Max Act: 1.3256. Min Act: -0.0001

Data Index: 171505 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 1.7527. Min Range: -1.7527

Max Act: 1.3597. Min Act: -0.0001

Data Index: 1351786 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 1.7527. Min Range: -1.7527

Max Act: 1.2977. Min Act: -0.0001

Data Index: 887645 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 1.7527. Min Range: -1.7527

Max Act: 1.2725. Min Act: -0.0000

Data Index: 253186 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 1.7527. Min Range: -1.7527

Max Act: 1.1548. Min Act: -0.0001

Data Index: 833388 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 1.7527. Min Range: -1.7527

Max Act: 1.3733. Min Act: -0.0001

Data Index: 296048 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 1.7527. Min Range: -1.7527

Max Act: 1.2851. Min Act: -0.0001

Data Index: 532219 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 1.7527. Min Range: -1.7527

Max Act: 1.2812. Min Act: -0.0001

Data Index: 1153727 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 1.7527. Min Range: -1.7527

Max Act: 1.1320. Min Act: -0.0001

Data Index: 80718 (C4 (Web Text))

Max Activating Token Index: 714

Text #16

Max Range: 1.7527. Min Range: -1.7527

Max Act: 1.2311. Min Act: -0.0001

Data Index: 626387 (C4 (Web Text))

Max Activating Token Index: 537

Text #17

Max Range: 1.7527. Min Range: -1.7527

Max Act: 1.2579. Min Act: -0.0001

Data Index: 60486 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 1.7527. Min Range: -1.7527

Max Act: 1.1234. Min Act: -0.0001

Data Index: 603502 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 1.7527. Min Range: -1.7527

Max Act: 1.1697. Min Act: -0.0001

Data Index: 449131 (C4 (Web Text))

Max Activating Token Index: 845