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

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

Neuron 2352 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: 3.3799. Min Range: -3.3799

Max Act: 3.3799. Min Act: -0.0000

Data Index: 977032 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 3.3799. Min Range: -3.3799

Max Act: 3.3248. Min Act: 0.0000

Data Index: 1033337 (C4 (Web Text))

Max Activating Token Index: 788

Text #2

Max Range: 3.3799. Min Range: -3.3799

Max Act: 3.0595. Min Act: -0.0000

Data Index: 244315 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 3.3799. Min Range: -3.3799

Max Act: 2.8096. Min Act: 0.0000

Data Index: 1029241 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 3.3799. Min Range: -3.3799

Max Act: 3.0787. Min Act: -0.0000

Data Index: 204804 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 3.3799. Min Range: -3.3799

Max Act: 2.9144. Min Act: 0.0001

Data Index: 831874 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 3.3799. Min Range: -3.3799

Max Act: 2.7493. Min Act: -0.0000

Data Index: 886191 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 3.3799. Min Range: -3.3799

Max Act: 2.6032. Min Act: -0.0000

Data Index: 1227241 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 3.3799. Min Range: -3.3799

Max Act: 2.5783. Min Act: -0.0000

Data Index: 1198057 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 3.3799. Min Range: -3.3799

Max Act: 2.5311. Min Act: -0.0000

Data Index: 987490 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 3.3799. Min Range: -3.3799

Max Act: 2.4960. Min Act: 0.0000

Data Index: 146518 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 3.3799. Min Range: -3.3799

Max Act: 2.3551. Min Act: 0.0000

Data Index: 574214 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 3.3799. Min Range: -3.3799

Max Act: 2.4833. Min Act: -0.0000

Data Index: 964022 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 3.3799. Min Range: -3.3799

Max Act: 2.4188. Min Act: -0.0000

Data Index: 1352879 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 3.3799. Min Range: -3.3799

Max Act: 2.3785. Min Act: -0.0000

Data Index: 476723 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 3.3799. Min Range: -3.3799

Max Act: 2.3630. Min Act: 0.0000

Data Index: 1280042 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 3.3799. Min Range: -3.3799

Max Act: 2.3139. Min Act: -0.0000

Data Index: 899457 (C4 (Web Text))

Max Activating Token Index: 241

Text #17

Max Range: 3.3799. Min Range: -3.3799

Max Act: 2.4439. Min Act: 0.0000

Data Index: 179956 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 3.3799. Min Range: -3.3799

Max Act: 2.1861. Min Act: -0.0000

Data Index: 1176637 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 3.3799. Min Range: -3.3799

Max Act: 2.4207. Min Act: -0.0000

Data Index: 350310 (C4 (Web Text))

Max Activating Token Index: 214