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

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

Neuron 1874 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: 0.2755. Min Range: -0.2755

Max Act: 0.2755. Min Act: -0.0001

Data Index: 137074 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 0.2755. Min Range: -0.2755

Max Act: 0.2722. Min Act: -0.0000

Data Index: 399416 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 0.2755. Min Range: -0.2755

Max Act: 0.2658. Min Act: -0.0001

Data Index: 562855 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 0.2755. Min Range: -0.2755

Max Act: 0.2534. Min Act: -0.0000

Data Index: 1174872 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 0.2755. Min Range: -0.2755

Max Act: 0.2517. Min Act: -0.0000

Data Index: 10629 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 0.2755. Min Range: -0.2755

Max Act: 0.2357. Min Act: -0.0000

Data Index: 1240524 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 0.2755. Min Range: -0.2755

Max Act: 0.2343. Min Act: -0.0000

Data Index: 835600 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 0.2755. Min Range: -0.2755

Max Act: 0.2350. Min Act: -0.0000

Data Index: 1146918 (C4 (Web Text))

Max Activating Token Index: 460

Text #8

Max Range: 0.2755. Min Range: -0.2755

Max Act: 0.2323. Min Act: -0.0000

Data Index: 1213747 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 0.2755. Min Range: -0.2755

Max Act: 0.2299. Min Act: -0.0000

Data Index: 912431 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 0.2755. Min Range: -0.2755

Max Act: 0.2295. Min Act: -0.0000

Data Index: 1033469 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 0.2755. Min Range: -0.2755

Max Act: 0.2228. Min Act: -0.0001

Data Index: 701528 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 0.2755. Min Range: -0.2755

Max Act: 0.2224. Min Act: -0.0000

Data Index: 458586 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 0.2755. Min Range: -0.2755

Max Act: 0.1825. Min Act: -0.0001

Data Index: 888310 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 0.2755. Min Range: -0.2755

Max Act: 0.2331. Min Act: -0.0000

Data Index: 1072633 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 0.2755. Min Range: -0.2755

Max Act: 0.2027. Min Act: -0.0000

Data Index: 739045 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 0.2755. Min Range: -0.2755

Max Act: 0.2141. Min Act: -0.0001

Data Index: 990261 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 0.2755. Min Range: -0.2755

Max Act: 0.2133. Min Act: -0.0000

Data Index: 502483 (C4 (Web Text))

Max Activating Token Index: 546

Text #18

Max Range: 0.2755. Min Range: -0.2755

Max Act: 0.2138. Min Act: -0.0000

Data Index: 345822 (C4 (Web Text))

Max Activating Token Index: 531

Text #19

Max Range: 0.2755. Min Range: -0.2755

Max Act: 0.2123. Min Act: -0.0001

Data Index: 972365 (C4 (Web Text))

Max Activating Token Index: 146