Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3497 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3043. Min Range: -0.3043

Max Act: 0.3043. Min Act: -0.0000

Data Index: 22988 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 0.3043. Min Range: -0.3043

Max Act: 0.2824. Min Act: -0.0000

Data Index: 555154 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 0.3043. Min Range: -0.3043

Max Act: 0.2448. Min Act: -0.0000

Data Index: 613308 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 0.3043. Min Range: -0.3043

Max Act: 0.2405. Min Act: 0.0001

Data Index: 1339531 (C4 (Web Text))

Max Activating Token Index: 140

Text #4

Max Range: 0.3043. Min Range: -0.3043

Max Act: 0.2306. Min Act: 0.0000

Data Index: 1358347 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 0.3043. Min Range: -0.3043

Max Act: 0.2334. Min Act: -0.0000

Data Index: 87426 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 0.3043. Min Range: -0.3043

Max Act: 0.2209. Min Act: 0.0000

Data Index: 1021424 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 0.3043. Min Range: -0.3043

Max Act: 0.2271. Min Act: 0.0000

Data Index: 1055334 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 0.3043. Min Range: -0.3043

Max Act: 0.2166. Min Act: 0.0000

Data Index: 208160 (C4 (Web Text))

Max Activating Token Index: 765

Text #9

Max Range: 0.3043. Min Range: -0.3043

Max Act: 0.2125. Min Act: -0.0000

Data Index: 28768 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 0.3043. Min Range: -0.3043

Max Act: 0.2093. Min Act: -0.0000

Data Index: 568922 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 0.3043. Min Range: -0.3043

Max Act: 0.2039. Min Act: -0.0000

Data Index: 702905 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 0.3043. Min Range: -0.3043

Max Act: 0.1958. Min Act: -0.0000

Data Index: 107321 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 0.3043. Min Range: -0.3043

Max Act: 0.1956. Min Act: -0.0000

Data Index: 603167 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 0.3043. Min Range: -0.3043

Max Act: 0.1894. Min Act: -0.0000

Data Index: 386692 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 0.3043. Min Range: -0.3043

Max Act: 0.1878. Min Act: 0.0000

Data Index: 273232 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 0.3043. Min Range: -0.3043

Max Act: 0.1857. Min Act: -0.0000

Data Index: 1061773 (C4 (Web Text))

Max Activating Token Index: 940

Text #17

Max Range: 0.3043. Min Range: -0.3043

Max Act: 0.1917. Min Act: -0.0000

Data Index: 818829 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 0.3043. Min Range: -0.3043

Max Act: 0.1504. Min Act: -0.0000

Data Index: 1194597 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 0.3043. Min Range: -0.3043

Max Act: 0.1870. Min Act: -0.0000

Data Index: 34174 (C4 (Web Text))

Max Activating Token Index: 701