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

Dataset: The Pile

Neuron 3526 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0089. Min Range: -1.0089

Max Act: 1.0089. Min Act: -0.0000

Data Index: 913722 (The Pile)

Max Activating Token Index: 20

Text #1

Max Range: 1.0089. Min Range: -1.0089

Max Act: 0.9215. Min Act: -0.0000

Data Index: 878891 (The Pile)

Max Activating Token Index: 161

Text #2

Max Range: 1.0089. Min Range: -1.0089

Max Act: 0.7226. Min Act: -0.0000

Data Index: 774046 (The Pile)

Max Activating Token Index: 433

Text #3

Max Range: 1.0089. Min Range: -1.0089

Max Act: 0.7719. Min Act: -0.0000

Data Index: 658414 (The Pile)

Max Activating Token Index: 30

Text #4

Max Range: 1.0089. Min Range: -1.0089

Max Act: 0.8024. Min Act: -0.0000

Data Index: 975947 (The Pile)

Max Activating Token Index: 580

Text #5

Max Range: 1.0089. Min Range: -1.0089

Max Act: 0.7367. Min Act: -0.0000

Data Index: 1672614 (The Pile)

Max Activating Token Index: 475

Text #6

Max Range: 1.0089. Min Range: -1.0089

Max Act: 0.7415. Min Act: -0.0000

Data Index: 138481 (The Pile)

Max Activating Token Index: 606

Text #7

Max Range: 1.0089. Min Range: -1.0089

Max Act: 0.7212. Min Act: -0.0000

Data Index: 68296 (The Pile)

Max Activating Token Index: 265

Text #8

Max Range: 1.0089. Min Range: -1.0089

Max Act: 0.6920. Min Act: -0.0000

Data Index: 1567418 (The Pile)

Max Activating Token Index: 175

Text #9

Max Range: 1.0089. Min Range: -1.0089

Max Act: 0.7087. Min Act: -0.0000

Data Index: 1836626 (The Pile)

Max Activating Token Index: 646

Text #10

Max Range: 1.0089. Min Range: -1.0089

Max Act: 0.6323. Min Act: -0.0000

Data Index: 1223834 (The Pile)

Max Activating Token Index: 913

Text #11

Max Range: 1.0089. Min Range: -1.0089

Max Act: 0.6318. Min Act: -0.0000

Data Index: 1383560 (The Pile)

Max Activating Token Index: 18

Text #12

Max Range: 1.0089. Min Range: -1.0089

Max Act: 0.6733. Min Act: -0.0000

Data Index: 524938 (The Pile)

Max Activating Token Index: 1009

Text #13

Max Range: 1.0089. Min Range: -1.0089

Max Act: 0.6668. Min Act: -0.0000

Data Index: 1548873 (The Pile)

Max Activating Token Index: 471

Text #14

Max Range: 1.0089. Min Range: -1.0089

Max Act: 0.6532. Min Act: -0.0000

Data Index: 578979 (The Pile)

Max Activating Token Index: 14

Text #15

Max Range: 1.0089. Min Range: -1.0089

Max Act: 0.6378. Min Act: -0.0000

Data Index: 1142723 (The Pile)

Max Activating Token Index: 356

Text #16

Max Range: 1.0089. Min Range: -1.0089

Max Act: 0.6375. Min Act: -0.0000

Data Index: 1151197 (The Pile)

Max Activating Token Index: 29

Text #17

Max Range: 1.0089. Min Range: -1.0089

Max Act: 0.6292. Min Act: -0.0000

Data Index: 1630732 (The Pile)

Max Activating Token Index: 525

Text #18

Max Range: 1.0089. Min Range: -1.0089

Max Act: 0.6297. Min Act: -0.0000

Data Index: 1379088 (The Pile)

Max Activating Token Index: 21

Text #19

Max Range: 1.0089. Min Range: -1.0089

Max Act: 0.6681. Min Act: -0.0000

Data Index: 892857 (The Pile)

Max Activating Token Index: 21