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

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

Neuron 3823 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2248. Min Range: -1.2248

Max Act: 1.2248. Min Act: -0.0000

Data Index: 1594429 (Python Code)

Max Activating Token Index: 850

Text #1

Max Range: 1.2248. Min Range: -1.2248

Max Act: 1.0230. Min Act: -0.0000

Data Index: 938047 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 1.2248. Min Range: -1.2248

Max Act: 0.9649. Min Act: -0.0000

Data Index: 1558604 (Python Code)

Max Activating Token Index: 875

Text #3

Max Range: 1.2248. Min Range: -1.2248

Max Act: 1.0320. Min Act: -0.0000

Data Index: 1554917 (Python Code)

Max Activating Token Index: 975

Text #4

Max Range: 1.2248. Min Range: -1.2248

Max Act: 0.9759. Min Act: -0.0000

Data Index: 698650 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 1.2248. Min Range: -1.2248

Max Act: 1.0604. Min Act: -0.0000

Data Index: 1639997 (Python Code)

Max Activating Token Index: 673

Text #6

Max Range: 1.2248. Min Range: -1.2248

Max Act: 0.9629. Min Act: -0.0000

Data Index: 1185692 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 1.2248. Min Range: -1.2248

Max Act: 0.9038. Min Act: -0.0000

Data Index: 871207 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 1.2248. Min Range: -1.2248

Max Act: 0.8957. Min Act: -0.0000

Data Index: 1421364 (Python Code)

Max Activating Token Index: 245

Text #9

Max Range: 1.2248. Min Range: -1.2248

Max Act: 0.9122. Min Act: -0.0000

Data Index: 1400408 (Python Code)

Max Activating Token Index: 192

Text #10

Max Range: 1.2248. Min Range: -1.2248

Max Act: 0.9984. Min Act: -0.0000

Data Index: 140377 (C4 (Web Text))

Max Activating Token Index: 499

Text #11

Max Range: 1.2248. Min Range: -1.2248

Max Act: 0.9932. Min Act: -0.0000

Data Index: 479164 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 1.2248. Min Range: -1.2248

Max Act: 0.9264. Min Act: -0.0000

Data Index: 1506720 (Python Code)

Max Activating Token Index: 135

Text #13

Max Range: 1.2248. Min Range: -1.2248

Max Act: 0.8684. Min Act: -0.0000

Data Index: 1590076 (Python Code)

Max Activating Token Index: 759

Text #14

Max Range: 1.2248. Min Range: -1.2248

Max Act: 0.9165. Min Act: -0.0000

Data Index: 34491 (C4 (Web Text))

Max Activating Token Index: 294

Text #15

Max Range: 1.2248. Min Range: -1.2248

Max Act: 0.8644. Min Act: -0.0000

Data Index: 1645195 (Python Code)

Max Activating Token Index: 210

Text #16

Max Range: 1.2248. Min Range: -1.2248

Max Act: 0.9493. Min Act: -0.0000

Data Index: 1577120 (Python Code)

Max Activating Token Index: 218

Text #17

Max Range: 1.2248. Min Range: -1.2248

Max Act: 0.8609. Min Act: -0.0000

Data Index: 1479321 (Python Code)

Max Activating Token Index: 245

Text #18

Max Range: 1.2248. Min Range: -1.2248

Max Act: 0.9610. Min Act: -0.0000

Data Index: 959652 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 1.2248. Min Range: -1.2248

Max Act: 0.8447. Min Act: -0.0000

Data Index: 277637 (C4 (Web Text))

Max Activating Token Index: 950