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

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

Neuron 3180 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: 2.5708. Min Range: -2.5708

Max Act: 2.5708. Min Act: -0.0000

Data Index: 22169 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 2.5708. Min Range: -2.5708

Max Act: 2.5626. Min Act: -0.0000

Data Index: 1185774 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 2.5708. Min Range: -2.5708

Max Act: 2.5193. Min Act: -0.0000

Data Index: 610218 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 2.5708. Min Range: -2.5708

Max Act: 2.3651. Min Act: -0.0000

Data Index: 444846 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 2.5708. Min Range: -2.5708

Max Act: 2.2033. Min Act: -0.0000

Data Index: 240657 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 2.5708. Min Range: -2.5708

Max Act: 2.1373. Min Act: -0.0000

Data Index: 304608 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 2.5708. Min Range: -2.5708

Max Act: 2.1128. Min Act: -0.0000

Data Index: 1464193 (Python Code)

Max Activating Token Index: 6

Text #7

Max Range: 2.5708. Min Range: -2.5708

Max Act: 2.0273. Min Act: -0.0000

Data Index: 1598909 (Python Code)

Max Activating Token Index: 478

Text #8

Max Range: 2.5708. Min Range: -2.5708

Max Act: 2.0395. Min Act: -0.0000

Data Index: 34715 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 2.5708. Min Range: -2.5708

Max Act: 2.0218. Min Act: -0.0000

Data Index: 907094 (C4 (Web Text))

Max Activating Token Index: 362

Text #10

Max Range: 2.5708. Min Range: -2.5708

Max Act: 2.1156. Min Act: -0.0000

Data Index: 1308043 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 2.5708. Min Range: -2.5708

Max Act: 1.9658. Min Act: -0.0000

Data Index: 395051 (C4 (Web Text))

Max Activating Token Index: 952

Text #12

Max Range: 2.5708. Min Range: -2.5708

Max Act: 1.9815. Min Act: -0.0000

Data Index: 1394989 (Python Code)

Max Activating Token Index: 424

Text #13

Max Range: 2.5708. Min Range: -2.5708

Max Act: 2.0538. Min Act: -0.0000

Data Index: 1525566 (Python Code)

Max Activating Token Index: 160

Text #14

Max Range: 2.5708. Min Range: -2.5708

Max Act: 1.8208. Min Act: -0.0000

Data Index: 479431 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 2.5708. Min Range: -2.5708

Max Act: 1.8092. Min Act: -0.0000

Data Index: 141232 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 2.5708. Min Range: -2.5708

Max Act: 1.8911. Min Act: -0.0000

Data Index: 1516847 (Python Code)

Max Activating Token Index: 996

Text #17

Max Range: 2.5708. Min Range: -2.5708

Max Act: 1.8974. Min Act: -0.0000

Data Index: 581698 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 2.5708. Min Range: -2.5708

Max Act: 1.8869. Min Act: -0.0000

Data Index: 22686 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 2.5708. Min Range: -2.5708

Max Act: 1.8571. Min Act: -0.0000

Data Index: 775438 (C4 (Web Text))

Max Activating Token Index: 92