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

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

Neuron 499 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: 0.2150. Min Range: -0.2150

Max Act: 0.2135. Min Act: -0.0002

Data Index: 318991 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.2150. Min Act: -0.0002

Data Index: 1056401 (C4 (Web Text))

Max Activating Token Index: 537

Text #2

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.2118. Min Act: -0.0002

Data Index: 893425 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.2064. Min Act: -0.0002

Data Index: 803389 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.2055. Min Act: -0.0002

Data Index: 684571 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1993. Min Act: -0.0002

Data Index: 1264231 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1987. Min Act: -0.0002

Data Index: 573637 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1986. Min Act: -0.0002

Data Index: 1134528 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1954. Min Act: -0.0002

Data Index: 839233 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1915. Min Act: -0.0002

Data Index: 6371 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1892. Min Act: -0.0002

Data Index: 1162088 (C4 (Web Text))

Max Activating Token Index: 147

Text #11

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1869. Min Act: -0.0002

Data Index: 1126935 (C4 (Web Text))

Max Activating Token Index: 507

Text #12

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1957. Min Act: -0.0002

Data Index: 324062 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1932. Min Act: -0.0002

Data Index: 383433 (C4 (Web Text))

Max Activating Token Index: 233

Text #14

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1835. Min Act: -0.0002

Data Index: 1143238 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1766. Min Act: -0.0002

Data Index: 805716 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1846. Min Act: -0.0002

Data Index: 1234091 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1837. Min Act: -0.0002

Data Index: 1139955 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1970. Min Act: -0.0002

Data Index: 512702 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1909. Min Act: -0.0002

Data Index: 422871 (C4 (Web Text))

Max Activating Token Index: 878