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

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

Neuron 1626 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: 0.2955. Min Range: -0.2955

Max Act: 0.2955. Min Act: -0.0000

Data Index: 622556 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2717. Min Act: -0.0001

Data Index: 150522 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2525. Min Act: -0.0000

Data Index: 1337417 (C4 (Web Text))

Max Activating Token Index: 939

Text #3

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2559. Min Act: -0.0001

Data Index: 1200319 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2490. Min Act: -0.0000

Data Index: 58947 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2456. Min Act: -0.0000

Data Index: 301735 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2430. Min Act: -0.0000

Data Index: 1053366 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2425. Min Act: -0.0000

Data Index: 192253 (C4 (Web Text))

Max Activating Token Index: 989

Text #8

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2282. Min Act: -0.0001

Data Index: 315747 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2359. Min Act: -0.0001

Data Index: 365343 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2344. Min Act: -0.0001

Data Index: 1285457 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2330. Min Act: -0.0001

Data Index: 704146 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2255. Min Act: -0.0001

Data Index: 611663 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2249. Min Act: -0.0000

Data Index: 321289 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2144. Min Act: -0.0001

Data Index: 415690 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2193. Min Act: -0.0000

Data Index: 865835 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2224. Min Act: -0.0000

Data Index: 185271 (C4 (Web Text))

Max Activating Token Index: 878

Text #17

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2215. Min Act: -0.0001

Data Index: 108988 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2072. Min Act: -0.0000

Data Index: 158296 (C4 (Web Text))

Max Activating Token Index: 888

Text #19

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2121. Min Act: -0.0001

Data Index: 682254 (C4 (Web Text))

Max Activating Token Index: 590