Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2912 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9962. Min Range: -1.9962

Max Act: 1.9962. Min Act: -0.0001

Data Index: 697685 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 1.9962. Min Range: -1.9962

Max Act: 1.5391. Min Act: -0.0000

Data Index: 1354496 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 1.9962. Min Range: -1.9962

Max Act: 1.5584. Min Act: -0.0000

Data Index: 1274554 (C4 (Web Text))

Max Activating Token Index: 425

Text #3

Max Range: 1.9962. Min Range: -1.9962

Max Act: 1.7702. Min Act: -0.0001

Data Index: 646213 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 1.9962. Min Range: -1.9962

Max Act: 1.5636. Min Act: -0.0000

Data Index: 641964 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 1.9962. Min Range: -1.9962

Max Act: 1.6018. Min Act: -0.0001

Data Index: 888023 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 1.9962. Min Range: -1.9962

Max Act: 1.5458. Min Act: -0.0000

Data Index: 280554 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 1.9962. Min Range: -1.9962

Max Act: 1.5688. Min Act: -0.0001

Data Index: 1024188 (C4 (Web Text))

Max Activating Token Index: 481

Text #8

Max Range: 1.9962. Min Range: -1.9962

Max Act: 1.4797. Min Act: -0.0000

Data Index: 1009609 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 1.9962. Min Range: -1.9962

Max Act: 1.4818. Min Act: -0.0001

Data Index: 1063388 (C4 (Web Text))

Max Activating Token Index: 831

Text #10

Max Range: 1.9962. Min Range: -1.9962

Max Act: 1.5361. Min Act: -0.0000

Data Index: 704500 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 1.9962. Min Range: -1.9962

Max Act: 1.5729. Min Act: -0.0001

Data Index: 383698 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 1.9962. Min Range: -1.9962

Max Act: 1.5348. Min Act: -0.0001

Data Index: 558282 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 1.9962. Min Range: -1.9962

Max Act: 1.5089. Min Act: -0.0000

Data Index: 1351236 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 1.9962. Min Range: -1.9962

Max Act: 1.5240. Min Act: -0.0001

Data Index: 1111068 (C4 (Web Text))

Max Activating Token Index: 246

Text #15

Max Range: 1.9962. Min Range: -1.9962

Max Act: 1.3858. Min Act: -0.0000

Data Index: 123066 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 1.9962. Min Range: -1.9962

Max Act: 1.5150. Min Act: -0.0001

Data Index: 930027 (C4 (Web Text))

Max Activating Token Index: 592

Text #17

Max Range: 1.9962. Min Range: -1.9962

Max Act: 1.4615. Min Act: -0.0000

Data Index: 435358 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 1.9962. Min Range: -1.9962

Max Act: 1.3794. Min Act: -0.0000

Data Index: 180934 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 1.9962. Min Range: -1.9962

Max Act: 1.4823. Min Act: -0.0001

Data Index: 745074 (C4 (Web Text))

Max Activating Token Index: 82