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

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

Neuron 2256 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.2061. Min Act: -0.0000

Data Index: 636848 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.2114. Min Act: -0.0000

Data Index: 1349054 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1910. Min Act: -0.0000

Data Index: 426466 (C4 (Web Text))

Max Activating Token Index: 344

Text #3

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.2060. Min Act: -0.0000

Data Index: 1342690 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.2062. Min Act: -0.0000

Data Index: 710320 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.2032. Min Act: -0.0000

Data Index: 1319911 (C4 (Web Text))

Max Activating Token Index: 907

Text #6

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.2024. Min Act: -0.0000

Data Index: 579600 (C4 (Web Text))

Max Activating Token Index: 503

Text #7

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.2064. Min Act: -0.0000

Data Index: 782422 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.2018. Min Act: -0.0000

Data Index: 1097322 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1857. Min Act: -0.0000

Data Index: 662473 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1911. Min Act: -0.0000

Data Index: 463693 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1894. Min Act: -0.0000

Data Index: 611550 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1753. Min Act: -0.0000

Data Index: 1183165 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1938. Min Act: -0.0000

Data Index: 87945 (C4 (Web Text))

Max Activating Token Index: 758

Text #14

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1850. Min Act: -0.0000

Data Index: 109502 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1959. Min Act: -0.0000

Data Index: 460465 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1808. Min Act: -0.0000

Data Index: 645288 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1863. Min Act: -0.0000

Data Index: 726023 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1793. Min Act: -0.0000

Data Index: 284913 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1791. Min Act: -0.0000

Data Index: 939091 (C4 (Web Text))

Max Activating Token Index: 516