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

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

Neuron 2017 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: 2.0594. Min Range: -2.0594

Max Act: 1.8008. Min Act: -0.0000

Data Index: 621444 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 2.0594. Min Range: -2.0594

Max Act: 1.8918. Min Act: -0.0000

Data Index: 79044 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 2.0594. Min Range: -2.0594

Max Act: 2.0594. Min Act: 0.0000

Data Index: 936081 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 2.0594. Min Range: -2.0594

Max Act: 1.8039. Min Act: -0.0000

Data Index: 1228426 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 2.0594. Min Range: -2.0594

Max Act: 1.9248. Min Act: -0.0000

Data Index: 1172507 (C4 (Web Text))

Max Activating Token Index: 920

Text #5

Max Range: 2.0594. Min Range: -2.0594

Max Act: 1.7662. Min Act: -0.0000

Data Index: 852627 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 2.0594. Min Range: -2.0594

Max Act: 1.7414. Min Act: -0.0000

Data Index: 124585 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 2.0594. Min Range: -2.0594

Max Act: 1.5114. Min Act: -0.0000

Data Index: 1133300 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 2.0594. Min Range: -2.0594

Max Act: 1.5048. Min Act: 0.0000

Data Index: 292476 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 2.0594. Min Range: -2.0594

Max Act: 1.4019. Min Act: -0.0000

Data Index: 851608 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 2.0594. Min Range: -2.0594

Max Act: 1.5682. Min Act: -0.0000

Data Index: 519862 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 2.0594. Min Range: -2.0594

Max Act: 1.4886. Min Act: -0.0000

Data Index: 64461 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 2.0594. Min Range: -2.0594

Max Act: 1.4478. Min Act: -0.0000

Data Index: 815496 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 2.0594. Min Range: -2.0594

Max Act: 1.4504. Min Act: 0.0000

Data Index: 1032781 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 2.0594. Min Range: -2.0594

Max Act: 1.5442. Min Act: -0.0000

Data Index: 102606 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 2.0594. Min Range: -2.0594

Max Act: 1.3683. Min Act: -0.0000

Data Index: 1320195 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 2.0594. Min Range: -2.0594

Max Act: 1.4286. Min Act: -0.0000

Data Index: 207376 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 2.0594. Min Range: -2.0594

Max Act: 1.2892. Min Act: 0.0000

Data Index: 959027 (C4 (Web Text))

Max Activating Token Index: 347

Text #18

Max Range: 2.0594. Min Range: -2.0594

Max Act: 1.2666. Min Act: -0.0000

Data Index: 24724 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 2.0594. Min Range: -2.0594

Max Act: 1.4228. Min Act: 0.0000

Data Index: 1341003 (C4 (Web Text))

Max Activating Token Index: 633