Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1638 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2853. Min Range: -0.2853

Max Act: 0.2853. Min Act: -0.0002

Data Index: 62822 (C4 (Web Text))

Max Activating Token Index: 376

Text #1

Max Range: 0.2853. Min Range: -0.2853

Max Act: 0.2335. Min Act: -0.0002

Data Index: 1356026 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 0.2853. Min Range: -0.2853

Max Act: 0.2411. Min Act: -0.0002

Data Index: 1211673 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 0.2853. Min Range: -0.2853

Max Act: 0.2236. Min Act: -0.0002

Data Index: 84167 (C4 (Web Text))

Max Activating Token Index: 1020

Text #4

Max Range: 0.2853. Min Range: -0.2853

Max Act: 0.2126. Min Act: -0.0002

Data Index: 539087 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 0.2853. Min Range: -0.2853

Max Act: 0.2169. Min Act: -0.0002

Data Index: 194060 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 0.2853. Min Range: -0.2853

Max Act: 0.2214. Min Act: -0.0002

Data Index: 40735 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 0.2853. Min Range: -0.2853

Max Act: 0.2198. Min Act: -0.0002

Data Index: 1133984 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 0.2853. Min Range: -0.2853

Max Act: 0.2275. Min Act: -0.0002

Data Index: 174258 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 0.2853. Min Range: -0.2853

Max Act: 0.2080. Min Act: -0.0002

Data Index: 1061783 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 0.2853. Min Range: -0.2853

Max Act: 0.2045. Min Act: -0.0002

Data Index: 938845 (C4 (Web Text))

Max Activating Token Index: 966

Text #11

Max Range: 0.2853. Min Range: -0.2853

Max Act: 0.1919. Min Act: -0.0002

Data Index: 205919 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 0.2853. Min Range: -0.2853

Max Act: 0.1966. Min Act: -0.0002

Data Index: 636013 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 0.2853. Min Range: -0.2853

Max Act: 0.2021. Min Act: -0.0002

Data Index: 409167 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 0.2853. Min Range: -0.2853

Max Act: 0.1939. Min Act: -0.0002

Data Index: 1143619 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 0.2853. Min Range: -0.2853

Max Act: 0.2019. Min Act: -0.0002

Data Index: 1302438 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 0.2853. Min Range: -0.2853

Max Act: 0.1853. Min Act: -0.0002

Data Index: 949177 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 0.2853. Min Range: -0.2853

Max Act: 0.1991. Min Act: -0.0002

Data Index: 131301 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 0.2853. Min Range: -0.2853

Max Act: 0.1967. Min Act: -0.0002

Data Index: 1353399 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 0.2853. Min Range: -0.2853

Max Act: 0.2027. Min Act: -0.0002

Data Index: 823212 (C4 (Web Text))

Max Activating Token Index: 225