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

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

Neuron 4181 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1345. Min Range: -4.1345

Max Act: 4.1345. Min Act: -0.0000

Data Index: 715889 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 4.1345. Min Range: -4.1345

Max Act: 3.7622. Min Act: -0.0000

Data Index: 345991 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 4.1345. Min Range: -4.1345

Max Act: 3.7722. Min Act: -0.0000

Data Index: 1269190 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 4.1345. Min Range: -4.1345

Max Act: 3.3232. Min Act: -0.0000

Data Index: 757156 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 4.1345. Min Range: -4.1345

Max Act: 3.4434. Min Act: -0.0000

Data Index: 298956 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 4.1345. Min Range: -4.1345

Max Act: 3.5932. Min Act: -0.0000

Data Index: 674911 (C4 (Web Text))

Max Activating Token Index: 731

Text #6

Max Range: 4.1345. Min Range: -4.1345

Max Act: 3.4396. Min Act: -0.0000

Data Index: 1314340 (C4 (Web Text))

Max Activating Token Index: 931

Text #7

Max Range: 4.1345. Min Range: -4.1345

Max Act: 3.3517. Min Act: -0.0000

Data Index: 1253854 (C4 (Web Text))

Max Activating Token Index: 558

Text #8

Max Range: 4.1345. Min Range: -4.1345

Max Act: 3.3151. Min Act: -0.0000

Data Index: 228110 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 4.1345. Min Range: -4.1345

Max Act: 3.2859. Min Act: -0.0000

Data Index: 961125 (C4 (Web Text))

Max Activating Token Index: 476

Text #10

Max Range: 4.1345. Min Range: -4.1345

Max Act: 3.3117. Min Act: -0.0000

Data Index: 7918 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 4.1345. Min Range: -4.1345

Max Act: 3.4206. Min Act: -0.0000

Data Index: 364127 (C4 (Web Text))

Max Activating Token Index: 730

Text #12

Max Range: 4.1345. Min Range: -4.1345

Max Act: 3.1196. Min Act: -0.0000

Data Index: 899633 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 4.1345. Min Range: -4.1345

Max Act: 3.2996. Min Act: -0.0000

Data Index: 1224153 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 4.1345. Min Range: -4.1345

Max Act: 3.2897. Min Act: -0.0000

Data Index: 108140 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 4.1345. Min Range: -4.1345

Max Act: 2.9682. Min Act: -0.0000

Data Index: 835824 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 4.1345. Min Range: -4.1345

Max Act: 3.1001. Min Act: -0.0000

Data Index: 594713 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 4.1345. Min Range: -4.1345

Max Act: 2.9002. Min Act: -0.0000

Data Index: 478816 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 4.1345. Min Range: -4.1345

Max Act: 3.0156. Min Act: -0.0000

Data Index: 232297 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 4.1345. Min Range: -4.1345

Max Act: 2.8628. Min Act: -0.0000

Data Index: 165326 (C4 (Web Text))

Max Activating Token Index: 446