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

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

Neuron 3062 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0121. Min Range: -1.0121

Max Act: 1.0121. Min Act: -0.0000

Data Index: 1109802 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.9612. Min Act: -0.0000

Data Index: 715351 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.8917. Min Act: -0.0000

Data Index: 109727 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.8656. Min Act: -0.0000

Data Index: 927414 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.8189. Min Act: -0.0000

Data Index: 1156869 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.7826. Min Act: -0.0000

Data Index: 492395 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.7566. Min Act: -0.0000

Data Index: 467721 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.7192. Min Act: -0.0000

Data Index: 199940 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.7561. Min Act: -0.0000

Data Index: 165876 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.7145. Min Act: -0.0000

Data Index: 971699 (C4 (Web Text))

Max Activating Token Index: 622

Text #10

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.7189. Min Act: -0.0000

Data Index: 679433 (C4 (Web Text))

Max Activating Token Index: 374

Text #11

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.6742. Min Act: -0.0000

Data Index: 513033 (C4 (Web Text))

Max Activating Token Index: 772

Text #12

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.6430. Min Act: -0.0000

Data Index: 298804 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.6878. Min Act: -0.0000

Data Index: 1177545 (C4 (Web Text))

Max Activating Token Index: 798

Text #14

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.6722. Min Act: -0.0000

Data Index: 1614837 (Python Code)

Max Activating Token Index: 88

Text #15

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.7106. Min Act: -0.0000

Data Index: 302355 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.6131. Min Act: -0.0000

Data Index: 746353 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.6024. Min Act: -0.0000

Data Index: 99508 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.5902. Min Act: -0.0000

Data Index: 1244106 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 1.0121. Min Range: -1.0121

Max Act: 0.5793. Min Act: -0.0000

Data Index: 762022 (C4 (Web Text))

Max Activating Token Index: 140