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

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

Neuron 4026 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: 0.6133. Min Range: -0.6133

Max Act: 0.6133. Min Act: -0.0000

Data Index: 413942 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.5932. Min Act: -0.0000

Data Index: 1169269 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.5475. Min Act: -0.0000

Data Index: 606253 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.5383. Min Act: -0.0000

Data Index: 951412 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.5127. Min Act: -0.0000

Data Index: 353663 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.5684. Min Act: -0.0000

Data Index: 12973 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.5021. Min Act: -0.0000

Data Index: 986760 (C4 (Web Text))

Max Activating Token Index: 798

Text #7

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.4928. Min Act: -0.0000

Data Index: 1210451 (C4 (Web Text))

Max Activating Token Index: 400

Text #8

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.4948. Min Act: -0.0000

Data Index: 505829 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.5027. Min Act: -0.0000

Data Index: 168436 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.5077. Min Act: -0.0000

Data Index: 593003 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.4791. Min Act: 0.0000

Data Index: 462772 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.5169. Min Act: -0.0000

Data Index: 284562 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.4725. Min Act: -0.0000

Data Index: 251372 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.5060. Min Act: -0.0000

Data Index: 53025 (C4 (Web Text))

Max Activating Token Index: 666

Text #15

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.4597. Min Act: -0.0000

Data Index: 262706 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.4479. Min Act: -0.0000

Data Index: 563450 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.4765. Min Act: -0.0000

Data Index: 351131 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.4673. Min Act: -0.0000

Data Index: 1012483 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 0.6133. Min Range: -0.6133

Max Act: 0.4635. Min Act: -0.0000

Data Index: 897870 (C4 (Web Text))

Max Activating Token Index: 716