Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 837 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2385. Min Act: -0.0000

Data Index: 394144 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2235. Min Act: -0.0000

Data Index: 107451 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2216. Min Act: -0.0000

Data Index: 259094 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2034. Min Act: -0.0000

Data Index: 1246450 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2081. Min Act: -0.0000

Data Index: 1132257 (C4 (Web Text))

Max Activating Token Index: 985

Text #5

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2063. Min Act: -0.0000

Data Index: 1055465 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2022. Min Act: -0.0000

Data Index: 195483 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.2151. Min Act: -0.0000

Data Index: 448086 (C4 (Web Text))

Max Activating Token Index: 875

Text #8

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.1926. Min Act: -0.0000

Data Index: 982191 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.1953. Min Act: 0.0001

Data Index: 67562 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.1833. Min Act: -0.0000

Data Index: 1176187 (C4 (Web Text))

Max Activating Token Index: 139

Text #11

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.1841. Min Act: -0.0000

Data Index: 903627 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.1831. Min Act: -0.0000

Data Index: 174541 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.1736. Min Act: -0.0000

Data Index: 654768 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.1739. Min Act: -0.0000

Data Index: 424184 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.1840. Min Act: -0.0000

Data Index: 863764 (C4 (Web Text))

Max Activating Token Index: 998

Text #16

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.1781. Min Act: -0.0000

Data Index: 214434 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.1769. Min Act: -0.0000

Data Index: 496481 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.1735. Min Act: -0.0000

Data Index: 791775 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 0.2385. Min Range: -0.2385

Max Act: 0.1673. Min Act: -0.0000

Data Index: 980672 (C4 (Web Text))

Max Activating Token Index: 602