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

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

Neuron 3507 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: 0.4719. Min Range: -0.4719

Max Act: 0.4719. Min Act: -0.0001

Data Index: 1354105 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.4719. Min Range: -0.4719

Max Act: 0.4647. Min Act: -0.0001

Data Index: 726332 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 0.4719. Min Range: -0.4719

Max Act: 0.3764. Min Act: -0.0002

Data Index: 1040142 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 0.4719. Min Range: -0.4719

Max Act: 0.3702. Min Act: -0.0002

Data Index: 914639 (C4 (Web Text))

Max Activating Token Index: 927

Text #4

Max Range: 0.4719. Min Range: -0.4719

Max Act: 0.3679. Min Act: -0.0002

Data Index: 54083 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 0.4719. Min Range: -0.4719

Max Act: 0.3676. Min Act: -0.0002

Data Index: 470981 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 0.4719. Min Range: -0.4719

Max Act: 0.3697. Min Act: -0.0001

Data Index: 1055209 (C4 (Web Text))

Max Activating Token Index: 399

Text #7

Max Range: 0.4719. Min Range: -0.4719

Max Act: 0.3416. Min Act: -0.0002

Data Index: 1057074 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 0.4719. Min Range: -0.4719

Max Act: 0.3282. Min Act: -0.0001

Data Index: 657077 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 0.4719. Min Range: -0.4719

Max Act: 0.3294. Min Act: -0.0001

Data Index: 328223 (C4 (Web Text))

Max Activating Token Index: 365

Text #10

Max Range: 0.4719. Min Range: -0.4719

Max Act: 0.2959. Min Act: -0.0002

Data Index: 295859 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 0.4719. Min Range: -0.4719

Max Act: 0.3273. Min Act: -0.0001

Data Index: 1124653 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 0.4719. Min Range: -0.4719

Max Act: 0.2955. Min Act: -0.0002

Data Index: 1228077 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 0.4719. Min Range: -0.4719

Max Act: 0.3162. Min Act: -0.0002

Data Index: 933687 (C4 (Web Text))

Max Activating Token Index: 214

Text #14

Max Range: 0.4719. Min Range: -0.4719

Max Act: 0.3290. Min Act: -0.0002

Data Index: 763953 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 0.4719. Min Range: -0.4719

Max Act: 0.3009. Min Act: -0.0001

Data Index: 666118 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 0.4719. Min Range: -0.4719

Max Act: 0.3035. Min Act: -0.0002

Data Index: 669358 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 0.4719. Min Range: -0.4719

Max Act: 0.2923. Min Act: -0.0001

Data Index: 763007 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 0.4719. Min Range: -0.4719

Max Act: 0.3068. Min Act: -0.0001

Data Index: 669182 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 0.4719. Min Range: -0.4719

Max Act: 0.2845. Min Act: -0.0001

Data Index: 226680 (C4 (Web Text))

Max Activating Token Index: 234