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

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

Neuron 4493 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8886. Min Range: -3.8886

Max Act: 3.8159. Min Act: -0.0000

Data Index: 1036037 (C4 (Web Text))

Max Activating Token Index: 338

Text #1

Max Range: 3.8886. Min Range: -3.8886

Max Act: 3.8886. Min Act: -0.0000

Data Index: 480626 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 3.8886. Min Range: -3.8886

Max Act: 3.7385. Min Act: -0.0000

Data Index: 50227 (C4 (Web Text))

Max Activating Token Index: 241

Text #3

Max Range: 3.8886. Min Range: -3.8886

Max Act: 3.7250. Min Act: -0.0000

Data Index: 1051408 (C4 (Web Text))

Max Activating Token Index: 737

Text #4

Max Range: 3.8886. Min Range: -3.8886

Max Act: 3.6826. Min Act: -0.0000

Data Index: 485815 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 3.8886. Min Range: -3.8886

Max Act: 3.4611. Min Act: -0.0000

Data Index: 52114 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 3.8886. Min Range: -3.8886

Max Act: 3.4813. Min Act: -0.0000

Data Index: 755550 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 3.8886. Min Range: -3.8886

Max Act: 3.2143. Min Act: -0.0000

Data Index: 196701 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 3.8886. Min Range: -3.8886

Max Act: 3.1969. Min Act: -0.0000

Data Index: 226444 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 3.8886. Min Range: -3.8886

Max Act: 3.1127. Min Act: -0.0000

Data Index: 138173 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 3.8886. Min Range: -3.8886

Max Act: 3.0367. Min Act: -0.0000

Data Index: 896488 (C4 (Web Text))

Max Activating Token Index: 828

Text #11

Max Range: 3.8886. Min Range: -3.8886

Max Act: 3.3160. Min Act: -0.0000

Data Index: 1196539 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 3.8886. Min Range: -3.8886

Max Act: 3.0732. Min Act: -0.0000

Data Index: 579860 (C4 (Web Text))

Max Activating Token Index: 842

Text #13

Max Range: 3.8886. Min Range: -3.8886

Max Act: 2.9209. Min Act: -0.0000

Data Index: 165590 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 3.8886. Min Range: -3.8886

Max Act: 2.8970. Min Act: -0.0000

Data Index: 133875 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 3.8886. Min Range: -3.8886

Max Act: 3.1424. Min Act: -0.0000

Data Index: 905937 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 3.8886. Min Range: -3.8886

Max Act: 3.1163. Min Act: -0.0000

Data Index: 151740 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 3.8886. Min Range: -3.8886

Max Act: 2.9563. Min Act: -0.0000

Data Index: 972974 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 3.8886. Min Range: -3.8886

Max Act: 2.8263. Min Act: -0.0000

Data Index: 585441 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 3.8886. Min Range: -3.8886

Max Act: 2.9227. Min Act: -0.0000

Data Index: 405422 (C4 (Web Text))

Max Activating Token Index: 627