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

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

Neuron 2190 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.5966. Min Act: -0.0000

Data Index: 1224552 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.5515. Min Act: -0.0000

Data Index: 1120396 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.4685. Min Act: -0.0000

Data Index: 673638 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.4807. Min Act: -0.0000

Data Index: 860294 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.4457. Min Act: -0.0000

Data Index: 829686 (C4 (Web Text))

Max Activating Token Index: 667

Text #5

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.4226. Min Act: -0.0000

Data Index: 1029717 (C4 (Web Text))

Max Activating Token Index: 359

Text #6

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.4422. Min Act: -0.0000

Data Index: 1138162 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.4135. Min Act: -0.0000

Data Index: 1237862 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.4214. Min Act: -0.0000

Data Index: 55553 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.3834. Min Act: -0.0000

Data Index: 412044 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.3757. Min Act: -0.0000

Data Index: 1185157 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.3940. Min Act: -0.0000

Data Index: 1090616 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.3869. Min Act: -0.0000

Data Index: 527709 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.3932. Min Act: -0.0000

Data Index: 711905 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.3626. Min Act: -0.0000

Data Index: 436265 (C4 (Web Text))

Max Activating Token Index: 670

Text #15

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.3693. Min Act: -0.0000

Data Index: 659157 (C4 (Web Text))

Max Activating Token Index: 487

Text #16

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.3616. Min Act: -0.0000

Data Index: 83598 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.4125. Min Act: -0.0000

Data Index: 1274262 (C4 (Web Text))

Max Activating Token Index: 184

Text #18

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.3520. Min Act: -0.0000

Data Index: 1325181 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 0.5966. Min Range: -0.5966

Max Act: 0.3315. Min Act: -0.0000

Data Index: 765952 (C4 (Web Text))

Max Activating Token Index: 120