Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1558 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8869. Min Range: -1.8869

Max Act: 1.7814. Min Act: -0.0002

Data Index: 777306 (C4 (Web Text))

Max Activating Token Index: 499

Text #1

Max Range: 1.8869. Min Range: -1.8869

Max Act: 1.8869. Min Act: -0.0001

Data Index: 106000 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 1.8869. Min Range: -1.8869

Max Act: 1.8425. Min Act: -0.0001

Data Index: 85348 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 1.8869. Min Range: -1.8869

Max Act: 1.7878. Min Act: -0.0002

Data Index: 152344 (C4 (Web Text))

Max Activating Token Index: 925

Text #4

Max Range: 1.8869. Min Range: -1.8869

Max Act: 1.7670. Min Act: -0.0001

Data Index: 962619 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 1.8869. Min Range: -1.8869

Max Act: 1.7188. Min Act: -0.0001

Data Index: 988563 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 1.8869. Min Range: -1.8869

Max Act: 1.6645. Min Act: -0.0002

Data Index: 148217 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 1.8869. Min Range: -1.8869

Max Act: 1.5181. Min Act: -0.0002

Data Index: 561809 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 1.8869. Min Range: -1.8869

Max Act: 1.5589. Min Act: -0.0002

Data Index: 60140 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 1.8869. Min Range: -1.8869

Max Act: 1.4949. Min Act: -0.0002

Data Index: 1232825 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 1.8869. Min Range: -1.8869

Max Act: 1.5826. Min Act: -0.0002

Data Index: 1318001 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 1.8869. Min Range: -1.8869

Max Act: 1.5430. Min Act: -0.0001

Data Index: 939301 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 1.8869. Min Range: -1.8869

Max Act: 1.5412. Min Act: -0.0002

Data Index: 752214 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 1.8869. Min Range: -1.8869

Max Act: 1.4742. Min Act: -0.0002

Data Index: 932170 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 1.8869. Min Range: -1.8869

Max Act: 1.4098. Min Act: -0.0002

Data Index: 751216 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 1.8869. Min Range: -1.8869

Max Act: 1.5158. Min Act: -0.0001

Data Index: 177282 (C4 (Web Text))

Max Activating Token Index: 772

Text #16

Max Range: 1.8869. Min Range: -1.8869

Max Act: 1.3845. Min Act: -0.0002

Data Index: 511815 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 1.8869. Min Range: -1.8869

Max Act: 1.3697. Min Act: -0.0001

Data Index: 868052 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 1.8869. Min Range: -1.8869

Max Act: 1.3670. Min Act: -0.0002

Data Index: 1250286 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 1.8869. Min Range: -1.8869

Max Act: 1.3732. Min Act: -0.0002

Data Index: 437557 (C4 (Web Text))

Max Activating Token Index: 76