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

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

Neuron 86 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9906. Min Range: -1.9906

Max Act: 1.9906. Min Act: -0.0000

Data Index: 388304 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 1.9906. Min Range: -1.9906

Max Act: 1.6904. Min Act: -0.0000

Data Index: 654924 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 1.9906. Min Range: -1.9906

Max Act: 1.7205. Min Act: -0.0000

Data Index: 97962 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 1.9906. Min Range: -1.9906

Max Act: 1.4685. Min Act: -0.0000

Data Index: 146430 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 1.9906. Min Range: -1.9906

Max Act: 1.5132. Min Act: -0.0000

Data Index: 386323 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 1.9906. Min Range: -1.9906

Max Act: 1.5304. Min Act: -0.0000

Data Index: 858327 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 1.9906. Min Range: -1.9906

Max Act: 1.2513. Min Act: -0.0000

Data Index: 1242086 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 1.9906. Min Range: -1.9906

Max Act: 1.3918. Min Act: -0.0000

Data Index: 347321 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 1.9906. Min Range: -1.9906

Max Act: 1.3583. Min Act: -0.0000

Data Index: 1143474 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 1.9906. Min Range: -1.9906

Max Act: 1.3162. Min Act: -0.0000

Data Index: 985579 (C4 (Web Text))

Max Activating Token Index: 446

Text #10

Max Range: 1.9906. Min Range: -1.9906

Max Act: 1.3921. Min Act: -0.0000

Data Index: 151161 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 1.9906. Min Range: -1.9906

Max Act: 1.2671. Min Act: -0.0000

Data Index: 21635 (C4 (Web Text))

Max Activating Token Index: 623

Text #12

Max Range: 1.9906. Min Range: -1.9906

Max Act: 1.3678. Min Act: -0.0000

Data Index: 29526 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 1.9906. Min Range: -1.9906

Max Act: 1.2357. Min Act: -0.0000

Data Index: 689981 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 1.9906. Min Range: -1.9906

Max Act: 1.3116. Min Act: -0.0000

Data Index: 514465 (C4 (Web Text))

Max Activating Token Index: 960

Text #15

Max Range: 1.9906. Min Range: -1.9906

Max Act: 1.2400. Min Act: -0.0000

Data Index: 695156 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 1.9906. Min Range: -1.9906

Max Act: 1.1632. Min Act: -0.0000

Data Index: 993653 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 1.9906. Min Range: -1.9906

Max Act: 1.4322. Min Act: -0.0000

Data Index: 1069878 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 1.9906. Min Range: -1.9906

Max Act: 1.1967. Min Act: -0.0000

Data Index: 907043 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 1.9906. Min Range: -1.9906

Max Act: 1.2678. Min Act: -0.0000

Data Index: 738647 (C4 (Web Text))

Max Activating Token Index: 605