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

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

Neuron 1610 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1216. Min Range: -1.1216

Max Act: 1.1216. Min Act: -0.0002

Data Index: 684656 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 1.1216. Min Range: -1.1216

Max Act: 0.9969. Min Act: -0.0002

Data Index: 1321455 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 1.1216. Min Range: -1.1216

Max Act: 1.0443. Min Act: -0.0001

Data Index: 1150892 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 1.1216. Min Range: -1.1216

Max Act: 0.9007. Min Act: -0.0002

Data Index: 1275913 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 1.1216. Min Range: -1.1216

Max Act: 0.9514. Min Act: -0.0002

Data Index: 881102 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 1.1216. Min Range: -1.1216

Max Act: 0.8952. Min Act: -0.0002

Data Index: 1316141 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 1.1216. Min Range: -1.1216

Max Act: 0.9357. Min Act: -0.0002

Data Index: 785714 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 1.1216. Min Range: -1.1216

Max Act: 0.9352. Min Act: -0.0002

Data Index: 1208967 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 1.1216. Min Range: -1.1216

Max Act: 0.8924. Min Act: -0.0001

Data Index: 502360 (C4 (Web Text))

Max Activating Token Index: 973

Text #9

Max Range: 1.1216. Min Range: -1.1216

Max Act: 0.8656. Min Act: -0.0001

Data Index: 1311953 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 1.1216. Min Range: -1.1216

Max Act: 0.8969. Min Act: -0.0002

Data Index: 834975 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 1.1216. Min Range: -1.1216

Max Act: 0.8837. Min Act: -0.0002

Data Index: 188532 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 1.1216. Min Range: -1.1216

Max Act: 0.8020. Min Act: -0.0002

Data Index: 63417 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 1.1216. Min Range: -1.1216

Max Act: 0.8307. Min Act: -0.0002

Data Index: 941020 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 1.1216. Min Range: -1.1216

Max Act: 0.8204. Min Act: -0.0001

Data Index: 1209954 (C4 (Web Text))

Max Activating Token Index: 725

Text #15

Max Range: 1.1216. Min Range: -1.1216

Max Act: 0.8849. Min Act: -0.0001

Data Index: 1005405 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 1.1216. Min Range: -1.1216

Max Act: 0.8168. Min Act: -0.0001

Data Index: 1107292 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 1.1216. Min Range: -1.1216

Max Act: 0.8323. Min Act: -0.0002

Data Index: 1305503 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 1.1216. Min Range: -1.1216

Max Act: 0.8628. Min Act: -0.0001

Data Index: 621683 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 1.1216. Min Range: -1.1216

Max Act: 0.8751. Min Act: -0.0002

Data Index: 546208 (C4 (Web Text))

Max Activating Token Index: 115