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

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

Neuron 3441 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0592. Min Range: -2.0592

Max Act: 2.0592. Min Act: -0.0000

Data Index: 748546 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 2.0592. Min Range: -2.0592

Max Act: 1.8085. Min Act: -0.0000

Data Index: 131992 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 2.0592. Min Range: -2.0592

Max Act: 1.5070. Min Act: 0.0000

Data Index: 694869 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 2.0592. Min Range: -2.0592

Max Act: 1.4953. Min Act: -0.0000

Data Index: 142629 (C4 (Web Text))

Max Activating Token Index: 505

Text #4

Max Range: 2.0592. Min Range: -2.0592

Max Act: 1.4909. Min Act: -0.0000

Data Index: 922313 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 2.0592. Min Range: -2.0592

Max Act: 1.4386. Min Act: -0.0000

Data Index: 752540 (C4 (Web Text))

Max Activating Token Index: 982

Text #6

Max Range: 2.0592. Min Range: -2.0592

Max Act: 1.4924. Min Act: -0.0000

Data Index: 237379 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 2.0592. Min Range: -2.0592

Max Act: 1.4007. Min Act: -0.0000

Data Index: 808815 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 2.0592. Min Range: -2.0592

Max Act: 1.3892. Min Act: -0.0000

Data Index: 975135 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 2.0592. Min Range: -2.0592

Max Act: 1.3871. Min Act: -0.0000

Data Index: 366543 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 2.0592. Min Range: -2.0592

Max Act: 1.3674. Min Act: -0.0000

Data Index: 142358 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 2.0592. Min Range: -2.0592

Max Act: 1.3398. Min Act: -0.0000

Data Index: 1237170 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 2.0592. Min Range: -2.0592

Max Act: 1.3117. Min Act: -0.0000

Data Index: 183340 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 2.0592. Min Range: -2.0592

Max Act: 1.2842. Min Act: -0.0000

Data Index: 796278 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 2.0592. Min Range: -2.0592

Max Act: 1.3594. Min Act: -0.0000

Data Index: 192317 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 2.0592. Min Range: -2.0592

Max Act: 1.2621. Min Act: -0.0000

Data Index: 307685 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 2.0592. Min Range: -2.0592

Max Act: 1.2379. Min Act: -0.0000

Data Index: 790455 (C4 (Web Text))

Max Activating Token Index: 440

Text #17

Max Range: 2.0592. Min Range: -2.0592

Max Act: 1.1030. Min Act: -0.0000

Data Index: 889964 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 2.0592. Min Range: -2.0592

Max Act: 1.2191. Min Act: -0.0000

Data Index: 566009 (C4 (Web Text))

Max Activating Token Index: 554

Text #19

Max Range: 2.0592. Min Range: -2.0592

Max Act: 1.2997. Min Act: -0.0000

Data Index: 1502915 (Python Code)

Max Activating Token Index: 217