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

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

Neuron 390 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.4765. Min Act: -0.0000

Data Index: 780471 (C4 (Web Text))

Max Activating Token Index: 361

Text #1

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.4941. Min Act: -0.0000

Data Index: 178738 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.4606. Min Act: -0.0000

Data Index: 728195 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.4243. Min Act: -0.0000

Data Index: 530794 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.4145. Min Act: -0.0000

Data Index: 180136 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3967. Min Act: -0.0000

Data Index: 518575 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3832. Min Act: -0.0000

Data Index: 1158803 (C4 (Web Text))

Max Activating Token Index: 718

Text #7

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3963. Min Act: -0.0000

Data Index: 840230 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3866. Min Act: -0.0000

Data Index: 969065 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3748. Min Act: -0.0000

Data Index: 218789 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3595. Min Act: -0.0000

Data Index: 451749 (C4 (Web Text))

Max Activating Token Index: 484

Text #11

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3695. Min Act: -0.0000

Data Index: 696942 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3678. Min Act: -0.0000

Data Index: 197469 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3687. Min Act: -0.0000

Data Index: 1113332 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3792. Min Act: -0.0000

Data Index: 1047224 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3887. Min Act: -0.0000

Data Index: 614475 (C4 (Web Text))

Max Activating Token Index: 725

Text #16

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3614. Min Act: -0.0000

Data Index: 706112 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3464. Min Act: -0.0000

Data Index: 603393 (C4 (Web Text))

Max Activating Token Index: 413

Text #18

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3421. Min Act: -0.0000

Data Index: 1163253 (C4 (Web Text))

Max Activating Token Index: 547

Text #19

Max Range: 0.4941. Min Range: -0.4941

Max Act: 0.3511. Min Act: -0.0000

Data Index: 1017367 (C4 (Web Text))

Max Activating Token Index: 638