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

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

Neuron 750 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.2241. Min Act: -0.0003

Data Index: 120481 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.2166. Min Act: -0.0003

Data Index: 586160 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.2118. Min Act: -0.0003

Data Index: 109211 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.2083. Min Act: -0.0003

Data Index: 1324163 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1977. Min Act: -0.0003

Data Index: 389475 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.2095. Min Act: -0.0003

Data Index: 1225985 (C4 (Web Text))

Max Activating Token Index: 884

Text #6

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.2004. Min Act: -0.0003

Data Index: 100532 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1994. Min Act: -0.0003

Data Index: 20594 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1979. Min Act: -0.0003

Data Index: 680302 (C4 (Web Text))

Max Activating Token Index: 246

Text #9

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1972. Min Act: -0.0003

Data Index: 33758 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1950. Min Act: -0.0003

Data Index: 1304070 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1946. Min Act: -0.0003

Data Index: 307225 (C4 (Web Text))

Max Activating Token Index: 86

Text #12

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1949. Min Act: -0.0003

Data Index: 21808 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1941. Min Act: -0.0003

Data Index: 454660 (C4 (Web Text))

Max Activating Token Index: 643

Text #14

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1941. Min Act: -0.0003

Data Index: 179911 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1928. Min Act: -0.0003

Data Index: 1117987 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1847. Min Act: -0.0003

Data Index: 330895 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1905. Min Act: -0.0003

Data Index: 401461 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1901. Min Act: -0.0003

Data Index: 1268808 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 0.2241. Min Range: -0.2241

Max Act: 0.1896. Min Act: -0.0003

Data Index: 202478 (C4 (Web Text))

Max Activating Token Index: 345