Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4671 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.8057. Min Act: 0.0001

Data Index: 686099 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.7077. Min Act: -0.0000

Data Index: 884199 (C4 (Web Text))

Max Activating Token Index: 324

Text #2

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.7572. Min Act: -0.0000

Data Index: 180898 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.6430. Min Act: -0.0000

Data Index: 710940 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.6334. Min Act: -0.0000

Data Index: 1335946 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.6596. Min Act: -0.0000

Data Index: 788748 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.6188. Min Act: 0.0001

Data Index: 1273351 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.5990. Min Act: -0.0000

Data Index: 274189 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.6164. Min Act: -0.0000

Data Index: 801606 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.5639. Min Act: -0.0000

Data Index: 828235 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.5341. Min Act: -0.0000

Data Index: 1042622 (C4 (Web Text))

Max Activating Token Index: 631

Text #11

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.6068. Min Act: -0.0000

Data Index: 460818 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.5878. Min Act: -0.0000

Data Index: 1316366 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.5702. Min Act: -0.0000

Data Index: 1127480 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.5663. Min Act: 0.0001

Data Index: 157890 (C4 (Web Text))

Max Activating Token Index: 257

Text #15

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.5483. Min Act: 0.0000

Data Index: 699659 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.5461. Min Act: -0.0000

Data Index: 53765 (C4 (Web Text))

Max Activating Token Index: 695

Text #17

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.5470. Min Act: 0.0001

Data Index: 279598 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.5696. Min Act: -0.0000

Data Index: 98347 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.5415. Min Act: -0.0000

Data Index: 1278553 (C4 (Web Text))

Max Activating Token Index: 497