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

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

Neuron 1426 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0938. Min Act: -0.0001

Data Index: 779933 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0875. Min Act: -0.0001

Data Index: 779011 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0790. Min Act: -0.0001

Data Index: 358152 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0830. Min Act: -0.0001

Data Index: 283250 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0792. Min Act: -0.0001

Data Index: 1083678 (C4 (Web Text))

Max Activating Token Index: 519

Text #5

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0787. Min Act: -0.0001

Data Index: 1354760 (C4 (Web Text))

Max Activating Token Index: 587

Text #6

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0807. Min Act: -0.0001

Data Index: 332306 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0666. Min Act: -0.0001

Data Index: 536516 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0737. Min Act: -0.0001

Data Index: 1194728 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0722. Min Act: -0.0001

Data Index: 1327930 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0776. Min Act: -0.0001

Data Index: 1486858 (Python Code)

Max Activating Token Index: 63

Text #11

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0711. Min Act: -0.0001

Data Index: 627121 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0757. Min Act: -0.0001

Data Index: 401333 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0686. Min Act: -0.0001

Data Index: 1309425 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0729. Min Act: -0.0001

Data Index: 338090 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0674. Min Act: -0.0001

Data Index: 1512630 (Python Code)

Max Activating Token Index: 750

Text #16

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0703. Min Act: -0.0001

Data Index: 713188 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0645. Min Act: -0.0001

Data Index: 1169201 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0721. Min Act: -0.0001

Data Index: 802937 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0717. Min Act: -0.0001

Data Index: 782107 (C4 (Web Text))

Max Activating Token Index: 7