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

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

Neuron 2602 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: 2.0717. Min Range: -2.0717

Max Act: 2.0717. Min Act: -0.0000

Data Index: 1149598 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 2.0717. Min Range: -2.0717

Max Act: 1.8533. Min Act: -0.0000

Data Index: 985693 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 2.0717. Min Range: -2.0717

Max Act: 1.5564. Min Act: -0.0000

Data Index: 386120 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 2.0717. Min Range: -2.0717

Max Act: 1.6565. Min Act: -0.0000

Data Index: 1240300 (C4 (Web Text))

Max Activating Token Index: 708

Text #4

Max Range: 2.0717. Min Range: -2.0717

Max Act: 1.5651. Min Act: -0.0000

Data Index: 846820 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 2.0717. Min Range: -2.0717

Max Act: 1.5543. Min Act: -0.0000

Data Index: 998234 (C4 (Web Text))

Max Activating Token Index: 999

Text #6

Max Range: 2.0717. Min Range: -2.0717

Max Act: 1.4493. Min Act: -0.0000

Data Index: 816382 (C4 (Web Text))

Max Activating Token Index: 830

Text #7

Max Range: 2.0717. Min Range: -2.0717

Max Act: 1.6545. Min Act: -0.0000

Data Index: 234949 (C4 (Web Text))

Max Activating Token Index: 853

Text #8

Max Range: 2.0717. Min Range: -2.0717

Max Act: 1.4483. Min Act: -0.0000

Data Index: 588635 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 2.0717. Min Range: -2.0717

Max Act: 1.4756. Min Act: -0.0000

Data Index: 284729 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 2.0717. Min Range: -2.0717

Max Act: 1.3280. Min Act: -0.0000

Data Index: 267177 (C4 (Web Text))

Max Activating Token Index: 271

Text #11

Max Range: 2.0717. Min Range: -2.0717

Max Act: 1.5005. Min Act: -0.0000

Data Index: 1002397 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 2.0717. Min Range: -2.0717

Max Act: 1.4322. Min Act: -0.0000

Data Index: 336742 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 2.0717. Min Range: -2.0717

Max Act: 1.3145. Min Act: -0.0000

Data Index: 140313 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 2.0717. Min Range: -2.0717

Max Act: 1.3839. Min Act: -0.0000

Data Index: 930289 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 2.0717. Min Range: -2.0717

Max Act: 1.4110. Min Act: -0.0000

Data Index: 210223 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 2.0717. Min Range: -2.0717

Max Act: 1.2966. Min Act: -0.0000

Data Index: 729869 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 2.0717. Min Range: -2.0717

Max Act: 1.3785. Min Act: -0.0000

Data Index: 733899 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 2.0717. Min Range: -2.0717

Max Act: 1.2748. Min Act: -0.0000

Data Index: 1628108 (Python Code)

Max Activating Token Index: 190

Text #19

Max Range: 2.0717. Min Range: -2.0717

Max Act: 1.4514. Min Act: -0.0000

Data Index: 494637 (C4 (Web Text))

Max Activating Token Index: 595