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

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

Neuron 3842 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0890. Min Act: -0.0000

Data Index: 507644 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0837. Min Act: -0.0000

Data Index: 1167986 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0830. Min Act: -0.0000

Data Index: 668350 (C4 (Web Text))

Max Activating Token Index: 522

Text #3

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0739. Min Act: -0.0000

Data Index: 118199 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0784. Min Act: -0.0001

Data Index: 1069199 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0715. Min Act: -0.0001

Data Index: 658595 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0809. Min Act: -0.0001

Data Index: 578377 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0745. Min Act: -0.0000

Data Index: 965687 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0724. Min Act: -0.0000

Data Index: 39157 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0773. Min Act: -0.0001

Data Index: 193960 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0737. Min Act: -0.0000

Data Index: 964242 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0695. Min Act: -0.0000

Data Index: 1322244 (C4 (Web Text))

Max Activating Token Index: 398

Text #12

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0707. Min Act: -0.0000

Data Index: 911387 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0697. Min Act: -0.0001

Data Index: 14213 (C4 (Web Text))

Max Activating Token Index: 913

Text #14

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0672. Min Act: -0.0000

Data Index: 539263 (C4 (Web Text))

Max Activating Token Index: 403

Text #15

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0672. Min Act: -0.0001

Data Index: 1055929 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0689. Min Act: -0.0000

Data Index: 402015 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0634. Min Act: -0.0000

Data Index: 756855 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0619. Min Act: -0.0001

Data Index: 214147 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0677. Min Act: -0.0000

Data Index: 801987 (C4 (Web Text))

Max Activating Token Index: 342