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

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

Neuron 3530 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2759. Min Act: -0.0001

Data Index: 82028 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2322. Min Act: -0.0000

Data Index: 533282 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2157. Min Act: -0.0000

Data Index: 61881 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2395. Min Act: -0.0000

Data Index: 870962 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2242. Min Act: -0.0000

Data Index: 30980 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2136. Min Act: -0.0001

Data Index: 1111314 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1834. Min Act: -0.0000

Data Index: 875967 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1972. Min Act: -0.0000

Data Index: 154807 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2156. Min Act: -0.0000

Data Index: 18630 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2085. Min Act: -0.0000

Data Index: 571762 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1946. Min Act: -0.0000

Data Index: 1129097 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2008. Min Act: -0.0000

Data Index: 941141 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1970. Min Act: -0.0001

Data Index: 559692 (C4 (Web Text))

Max Activating Token Index: 378

Text #13

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1887. Min Act: -0.0000

Data Index: 488922 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1820. Min Act: -0.0000

Data Index: 40962 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1868. Min Act: -0.0000

Data Index: 1007229 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1979. Min Act: -0.0000

Data Index: 1253473 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1907. Min Act: -0.0000

Data Index: 966698 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1793. Min Act: -0.0000

Data Index: 431312 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1782. Min Act: -0.0001

Data Index: 722410 (C4 (Web Text))

Max Activating Token Index: 801