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

Dataset: The Pile

Neuron 3539 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2452. Min Range: -1.2452

Max Act: 1.2452. Min Act: -0.0000

Data Index: 479154 (The Pile)

Max Activating Token Index: 856

Text #1

Max Range: 1.2452. Min Range: -1.2452

Max Act: 0.9951. Min Act: -0.0000

Data Index: 51833 (The Pile)

Max Activating Token Index: 140

Text #2

Max Range: 1.2452. Min Range: -1.2452

Max Act: 1.0379. Min Act: -0.0000

Data Index: 1609931 (The Pile)

Max Activating Token Index: 176

Text #3

Max Range: 1.2452. Min Range: -1.2452

Max Act: 0.9862. Min Act: -0.0000

Data Index: 1365967 (The Pile)

Max Activating Token Index: 248

Text #4

Max Range: 1.2452. Min Range: -1.2452

Max Act: 0.8550. Min Act: -0.0000

Data Index: 452536 (The Pile)

Max Activating Token Index: 907

Text #5

Max Range: 1.2452. Min Range: -1.2452

Max Act: 0.9113. Min Act: -0.0000

Data Index: 1168463 (The Pile)

Max Activating Token Index: 63

Text #6

Max Range: 1.2452. Min Range: -1.2452

Max Act: 0.8238. Min Act: -0.0000

Data Index: 1545378 (The Pile)

Max Activating Token Index: 29

Text #7

Max Range: 1.2452. Min Range: -1.2452

Max Act: 0.7823. Min Act: -0.0000

Data Index: 190984 (The Pile)

Max Activating Token Index: 159

Text #8

Max Range: 1.2452. Min Range: -1.2452

Max Act: 0.8072. Min Act: -0.0000

Data Index: 1591564 (The Pile)

Max Activating Token Index: 729

Text #9

Max Range: 1.2452. Min Range: -1.2452

Max Act: 0.7835. Min Act: -0.0000

Data Index: 1324689 (The Pile)

Max Activating Token Index: 722

Text #10

Max Range: 1.2452. Min Range: -1.2452

Max Act: 0.8373. Min Act: -0.0000

Data Index: 185243 (The Pile)

Max Activating Token Index: 770

Text #11

Max Range: 1.2452. Min Range: -1.2452

Max Act: 0.8019. Min Act: -0.0000

Data Index: 1293664 (The Pile)

Max Activating Token Index: 977

Text #12

Max Range: 1.2452. Min Range: -1.2452

Max Act: 0.8309. Min Act: -0.0000

Data Index: 1963461 (The Pile)

Max Activating Token Index: 479

Text #13

Max Range: 1.2452. Min Range: -1.2452

Max Act: 0.8177. Min Act: -0.0000

Data Index: 1425169 (The Pile)

Max Activating Token Index: 234

Text #14

Max Range: 1.2452. Min Range: -1.2452

Max Act: 0.9684. Min Act: -0.0000

Data Index: 106863 (The Pile)

Max Activating Token Index: 401

Text #15

Max Range: 1.2452. Min Range: -1.2452

Max Act: 0.7041. Min Act: -0.0000

Data Index: 992081 (The Pile)

Max Activating Token Index: 707

Text #16

Max Range: 1.2452. Min Range: -1.2452

Max Act: 0.8198. Min Act: -0.0000

Data Index: 1779374 (The Pile)

Max Activating Token Index: 361

Text #17

Max Range: 1.2452. Min Range: -1.2452

Max Act: 0.6810. Min Act: -0.0000

Data Index: 1061450 (The Pile)

Max Activating Token Index: 25

Text #18

Max Range: 1.2452. Min Range: -1.2452

Max Act: 0.7613. Min Act: -0.0000

Data Index: 1783081 (The Pile)

Max Activating Token Index: 1020

Text #19

Max Range: 1.2452. Min Range: -1.2452

Max Act: 0.7363. Min Act: -0.0000

Data Index: 694334 (The Pile)

Max Activating Token Index: 874