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

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

Neuron 2433 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1035. Min Range: -2.1035

Max Act: 2.1035. Min Act: -0.0000

Data Index: 465560 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 2.1035. Min Range: -2.1035

Max Act: 2.0425. Min Act: -0.0000

Data Index: 561582 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.8657. Min Act: -0.0000

Data Index: 390929 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.8527. Min Act: -0.0000

Data Index: 1059347 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.9622. Min Act: -0.0000

Data Index: 148451 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.7523. Min Act: -0.0000

Data Index: 212941 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.8875. Min Act: -0.0000

Data Index: 1331937 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.6505. Min Act: 0.0000

Data Index: 247000 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.7394. Min Act: -0.0000

Data Index: 151902 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.7145. Min Act: -0.0000

Data Index: 849958 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.7049. Min Act: -0.0000

Data Index: 1283353 (C4 (Web Text))

Max Activating Token Index: 346

Text #11

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.7563. Min Act: -0.0000

Data Index: 813905 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.6751. Min Act: -0.0000

Data Index: 477773 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.7702. Min Act: -0.0000

Data Index: 568723 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.7501. Min Act: -0.0000

Data Index: 213819 (C4 (Web Text))

Max Activating Token Index: 909

Text #15

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.6473. Min Act: -0.0000

Data Index: 658105 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.6704. Min Act: -0.0000

Data Index: 685232 (C4 (Web Text))

Max Activating Token Index: 878

Text #17

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.6438. Min Act: -0.0000

Data Index: 782294 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.4987. Min Act: -0.0000

Data Index: 601874 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 2.1035. Min Range: -2.1035

Max Act: 1.5754. Min Act: -0.0000

Data Index: 888539 (C4 (Web Text))

Max Activating Token Index: 457