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

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

Neuron 1126 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.7306. Min Act: -0.0000

Data Index: 514644 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.6811. Min Act: -0.0000

Data Index: 912663 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.6945. Min Act: -0.0000

Data Index: 276782 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.6283. Min Act: -0.0000

Data Index: 59665 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.5629. Min Act: -0.0000

Data Index: 548045 (C4 (Web Text))

Max Activating Token Index: 981

Text #5

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.5380. Min Act: -0.0000

Data Index: 1167063 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.5490. Min Act: 0.0000

Data Index: 434990 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.5041. Min Act: -0.0000

Data Index: 132640 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.5137. Min Act: 0.0000

Data Index: 1185821 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.5045. Min Act: -0.0000

Data Index: 858066 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.4989. Min Act: -0.0000

Data Index: 451985 (C4 (Web Text))

Max Activating Token Index: 203

Text #11

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.4954. Min Act: -0.0000

Data Index: 704691 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.5101. Min Act: -0.0000

Data Index: 1222433 (C4 (Web Text))

Max Activating Token Index: 634

Text #13

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.5033. Min Act: -0.0000

Data Index: 484144 (C4 (Web Text))

Max Activating Token Index: 599

Text #14

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.4991. Min Act: -0.0000

Data Index: 1069407 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.4948. Min Act: -0.0000

Data Index: 400595 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.4777. Min Act: -0.0000

Data Index: 924810 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.4630. Min Act: 0.0001

Data Index: 747480 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.4694. Min Act: -0.0000

Data Index: 2208 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.4596. Min Act: -0.0000

Data Index: 1652340 (Python Code)

Max Activating Token Index: 959