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

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

Neuron 1966 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8200. Min Range: -0.8200

Max Act: 0.8200. Min Act: -0.0000

Data Index: 607036 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 0.8200. Min Range: -0.8200

Max Act: 0.8078. Min Act: -0.0000

Data Index: 632030 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 0.8200. Min Range: -0.8200

Max Act: 0.7169. Min Act: -0.0000

Data Index: 674069 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 0.8200. Min Range: -0.8200

Max Act: 0.6062. Min Act: -0.0000

Data Index: 1022227 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 0.8200. Min Range: -0.8200

Max Act: 0.6275. Min Act: -0.0000

Data Index: 652818 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 0.8200. Min Range: -0.8200

Max Act: 0.6036. Min Act: -0.0000

Data Index: 1278357 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 0.8200. Min Range: -0.8200

Max Act: 0.5612. Min Act: -0.0000

Data Index: 796913 (C4 (Web Text))

Max Activating Token Index: 801

Text #7

Max Range: 0.8200. Min Range: -0.8200

Max Act: 0.5801. Min Act: -0.0000

Data Index: 234861 (C4 (Web Text))

Max Activating Token Index: 631

Text #8

Max Range: 0.8200. Min Range: -0.8200

Max Act: 0.5661. Min Act: -0.0000

Data Index: 332239 (C4 (Web Text))

Max Activating Token Index: 489

Text #9

Max Range: 0.8200. Min Range: -0.8200

Max Act: 0.5792. Min Act: -0.0000

Data Index: 788181 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 0.8200. Min Range: -0.8200

Max Act: 0.5630. Min Act: -0.0000

Data Index: 294515 (C4 (Web Text))

Max Activating Token Index: 654

Text #11

Max Range: 0.8200. Min Range: -0.8200

Max Act: 0.5398. Min Act: -0.0000

Data Index: 945942 (C4 (Web Text))

Max Activating Token Index: 337

Text #12

Max Range: 0.8200. Min Range: -0.8200

Max Act: 0.5686. Min Act: -0.0000

Data Index: 1141040 (C4 (Web Text))

Max Activating Token Index: 170

Text #13

Max Range: 0.8200. Min Range: -0.8200

Max Act: 0.5271. Min Act: -0.0000

Data Index: 932944 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 0.8200. Min Range: -0.8200

Max Act: 0.5602. Min Act: -0.0000

Data Index: 1189141 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 0.8200. Min Range: -0.8200

Max Act: 0.5600. Min Act: -0.0000

Data Index: 298189 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 0.8200. Min Range: -0.8200

Max Act: 0.5406. Min Act: -0.0000

Data Index: 1126707 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 0.8200. Min Range: -0.8200

Max Act: 0.5397. Min Act: -0.0000

Data Index: 1061408 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 0.8200. Min Range: -0.8200

Max Act: 0.5240. Min Act: -0.0000

Data Index: 1176049 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 0.8200. Min Range: -0.8200

Max Act: 0.5579. Min Act: -0.0000

Data Index: 313454 (C4 (Web Text))

Max Activating Token Index: 71