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

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

Neuron 600 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3870. Min Range: -2.3870

Max Act: 2.3870. Min Act: -0.0000

Data Index: 909 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 2.3870. Min Range: -2.3870

Max Act: 2.3471. Min Act: -0.0000

Data Index: 401567 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 2.3870. Min Range: -2.3870

Max Act: 2.3556. Min Act: -0.0000

Data Index: 125393 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 2.3870. Min Range: -2.3870

Max Act: 2.2273. Min Act: -0.0000

Data Index: 154794 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 2.3870. Min Range: -2.3870

Max Act: 2.1861. Min Act: -0.0000

Data Index: 560145 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 2.3870. Min Range: -2.3870

Max Act: 2.2481. Min Act: -0.0000

Data Index: 272645 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 2.3870. Min Range: -2.3870

Max Act: 2.1244. Min Act: -0.0000

Data Index: 226104 (C4 (Web Text))

Max Activating Token Index: 955

Text #7

Max Range: 2.3870. Min Range: -2.3870

Max Act: 2.2082. Min Act: -0.0000

Data Index: 333030 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 2.3870. Min Range: -2.3870

Max Act: 2.3321. Min Act: -0.0000

Data Index: 738189 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 2.3870. Min Range: -2.3870

Max Act: 2.2006. Min Act: -0.0000

Data Index: 1214244 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 2.3870. Min Range: -2.3870

Max Act: 2.1678. Min Act: -0.0000

Data Index: 125424 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 2.3870. Min Range: -2.3870

Max Act: 2.0153. Min Act: -0.0000

Data Index: 355799 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 2.3870. Min Range: -2.3870

Max Act: 2.1213. Min Act: -0.0000

Data Index: 1098041 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 2.3870. Min Range: -2.3870

Max Act: 2.2327. Min Act: -0.0000

Data Index: 165880 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 2.3870. Min Range: -2.3870

Max Act: 2.0928. Min Act: -0.0000

Data Index: 142535 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 2.3870. Min Range: -2.3870

Max Act: 2.0810. Min Act: -0.0000

Data Index: 768351 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 2.3870. Min Range: -2.3870

Max Act: 2.1997. Min Act: -0.0000

Data Index: 1000626 (C4 (Web Text))

Max Activating Token Index: 766

Text #17

Max Range: 2.3870. Min Range: -2.3870

Max Act: 1.9651. Min Act: -0.0000

Data Index: 459322 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 2.3870. Min Range: -2.3870

Max Act: 2.0636. Min Act: -0.0000

Data Index: 609899 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 2.3870. Min Range: -2.3870

Max Act: 2.0390. Min Act: -0.0000

Data Index: 1173229 (C4 (Web Text))

Max Activating Token Index: 457