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

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

Neuron 104 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: 0.4940. Min Range: -0.4940

Max Act: 0.4940. Min Act: -0.0000

Data Index: 1072072 (C4 (Web Text))

Max Activating Token Index: 355

Text #1

Max Range: 0.4940. Min Range: -0.4940

Max Act: 0.4817. Min Act: -0.0000

Data Index: 1078288 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 0.4940. Min Range: -0.4940

Max Act: 0.4770. Min Act: -0.0000

Data Index: 5067 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 0.4940. Min Range: -0.4940

Max Act: 0.4348. Min Act: -0.0000

Data Index: 497928 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 0.4940. Min Range: -0.4940

Max Act: 0.4279. Min Act: -0.0000

Data Index: 516378 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 0.4940. Min Range: -0.4940

Max Act: 0.4033. Min Act: -0.0000

Data Index: 589107 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 0.4940. Min Range: -0.4940

Max Act: 0.4008. Min Act: -0.0000

Data Index: 210941 (C4 (Web Text))

Max Activating Token Index: 68

Text #7

Max Range: 0.4940. Min Range: -0.4940

Max Act: 0.4164. Min Act: 0.0000

Data Index: 539000 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 0.4940. Min Range: -0.4940

Max Act: 0.4085. Min Act: -0.0000

Data Index: 344902 (C4 (Web Text))

Max Activating Token Index: 419

Text #9

Max Range: 0.4940. Min Range: -0.4940

Max Act: 0.4128. Min Act: -0.0000

Data Index: 1032523 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 0.4940. Min Range: -0.4940

Max Act: 0.3975. Min Act: -0.0000

Data Index: 236276 (C4 (Web Text))

Max Activating Token Index: 726

Text #11

Max Range: 0.4940. Min Range: -0.4940

Max Act: 0.3724. Min Act: -0.0000

Data Index: 778862 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 0.4940. Min Range: -0.4940

Max Act: 0.3509. Min Act: -0.0000

Data Index: 87587 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 0.4940. Min Range: -0.4940

Max Act: 0.3680. Min Act: -0.0000

Data Index: 1173476 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 0.4940. Min Range: -0.4940

Max Act: 0.3621. Min Act: -0.0000

Data Index: 1162291 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 0.4940. Min Range: -0.4940

Max Act: 0.3532. Min Act: -0.0000

Data Index: 1075486 (C4 (Web Text))

Max Activating Token Index: 876

Text #16

Max Range: 0.4940. Min Range: -0.4940

Max Act: 0.3402. Min Act: -0.0000

Data Index: 1119721 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 0.4940. Min Range: -0.4940

Max Act: 0.3128. Min Act: -0.0000

Data Index: 741193 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 0.4940. Min Range: -0.4940

Max Act: 0.3564. Min Act: -0.0000

Data Index: 935571 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 0.4940. Min Range: -0.4940

Max Act: 0.3258. Min Act: -0.0000

Data Index: 59895 (C4 (Web Text))

Max Activating Token Index: 552