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

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

Neuron 4646 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2982. Min Range: -2.2982

Max Act: 2.2982. Min Act: -0.0000

Data Index: 1160007 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 2.2982. Min Range: -2.2982

Max Act: 2.2483. Min Act: -0.0000

Data Index: 1260967 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 2.2982. Min Range: -2.2982

Max Act: 1.8709. Min Act: -0.0000

Data Index: 816191 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 2.2982. Min Range: -2.2982

Max Act: 1.8393. Min Act: -0.0000

Data Index: 847429 (C4 (Web Text))

Max Activating Token Index: 440

Text #4

Max Range: 2.2982. Min Range: -2.2982

Max Act: 1.6634. Min Act: -0.0000

Data Index: 1264027 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 2.2982. Min Range: -2.2982

Max Act: 1.6742. Min Act: -0.0000

Data Index: 96635 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 2.2982. Min Range: -2.2982

Max Act: 1.5310. Min Act: -0.0000

Data Index: 343326 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 2.2982. Min Range: -2.2982

Max Act: 1.5241. Min Act: -0.0000

Data Index: 246094 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 2.2982. Min Range: -2.2982

Max Act: 1.5957. Min Act: -0.0000

Data Index: 635980 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 2.2982. Min Range: -2.2982

Max Act: 1.5052. Min Act: -0.0000

Data Index: 270329 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 2.2982. Min Range: -2.2982

Max Act: 1.5057. Min Act: 0.0000

Data Index: 1249537 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 2.2982. Min Range: -2.2982

Max Act: 1.4425. Min Act: -0.0000

Data Index: 603969 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 2.2982. Min Range: -2.2982

Max Act: 1.4348. Min Act: -0.0000

Data Index: 1188237 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 2.2982. Min Range: -2.2982

Max Act: 1.5337. Min Act: -0.0000

Data Index: 814620 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 2.2982. Min Range: -2.2982

Max Act: 1.4299. Min Act: -0.0000

Data Index: 677225 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 2.2982. Min Range: -2.2982

Max Act: 1.4156. Min Act: 0.0000

Data Index: 520067 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 2.2982. Min Range: -2.2982

Max Act: 1.4033. Min Act: 0.0000

Data Index: 414852 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 2.2982. Min Range: -2.2982

Max Act: 1.3043. Min Act: -0.0000

Data Index: 320660 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 2.2982. Min Range: -2.2982

Max Act: 1.2961. Min Act: -0.0000

Data Index: 845902 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 2.2982. Min Range: -2.2982

Max Act: 1.4749. Min Act: -0.0000

Data Index: 1240244 (C4 (Web Text))

Max Activating Token Index: 61