Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1328 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.8642. Min Act: -0.0000

Data Index: 1375965 (The Pile)

Max Activating Token Index: 178

Text #1

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.8774. Min Act: -0.0000

Data Index: 1457092 (The Pile)

Max Activating Token Index: 25

Text #2

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.7971. Min Act: -0.0000

Data Index: 1534876 (The Pile)

Max Activating Token Index: 798

Text #3

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.8205. Min Act: -0.0000

Data Index: 1815319 (The Pile)

Max Activating Token Index: 505

Text #4

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.7286. Min Act: -0.0000

Data Index: 1180114 (The Pile)

Max Activating Token Index: 98

Text #5

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.7254. Min Act: -0.0000

Data Index: 286101 (The Pile)

Max Activating Token Index: 715

Text #6

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.7515. Min Act: -0.0000

Data Index: 1008100 (The Pile)

Max Activating Token Index: 13

Text #7

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.7341. Min Act: -0.0000

Data Index: 443314 (The Pile)

Max Activating Token Index: 114

Text #8

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.7263. Min Act: -0.0000

Data Index: 891468 (The Pile)

Max Activating Token Index: 578

Text #9

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.7309. Min Act: -0.0000

Data Index: 383951 (The Pile)

Max Activating Token Index: 35

Text #10

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.7281. Min Act: -0.0000

Data Index: 496509 (The Pile)

Max Activating Token Index: 173

Text #11

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.6697. Min Act: -0.0000

Data Index: 1315686 (The Pile)

Max Activating Token Index: 133

Text #12

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.6632. Min Act: -0.0000

Data Index: 1240819 (The Pile)

Max Activating Token Index: 40

Text #13

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.7076. Min Act: -0.0000

Data Index: 1807725 (The Pile)

Max Activating Token Index: 763

Text #14

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.6842. Min Act: -0.0000

Data Index: 322428 (The Pile)

Max Activating Token Index: 148

Text #15

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.7262. Min Act: -0.0000

Data Index: 947496 (The Pile)

Max Activating Token Index: 107

Text #16

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.6727. Min Act: -0.0000

Data Index: 328064 (The Pile)

Max Activating Token Index: 229

Text #17

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.6766. Min Act: -0.0000

Data Index: 549698 (The Pile)

Max Activating Token Index: 643

Text #18

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.7429. Min Act: -0.0000

Data Index: 212714 (The Pile)

Max Activating Token Index: 235

Text #19

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.6883. Min Act: -0.0000

Data Index: 1273280 (The Pile)

Max Activating Token Index: 201