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

Dataset: The Pile

Neuron 1313 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4111. Min Range: -1.4111

Max Act: 1.4111. Min Act: -0.0000

Data Index: 1328369 (The Pile)

Max Activating Token Index: 456

Text #1

Max Range: 1.4111. Min Range: -1.4111

Max Act: 1.1172. Min Act: -0.0000

Data Index: 1798622 (The Pile)

Max Activating Token Index: 837

Text #2

Max Range: 1.4111. Min Range: -1.4111

Max Act: 1.0203. Min Act: -0.0000

Data Index: 1729812 (The Pile)

Max Activating Token Index: 335

Text #3

Max Range: 1.4111. Min Range: -1.4111

Max Act: 1.0102. Min Act: -0.0000

Data Index: 311812 (The Pile)

Max Activating Token Index: 80

Text #4

Max Range: 1.4111. Min Range: -1.4111

Max Act: 0.9741. Min Act: -0.0000

Data Index: 1665565 (The Pile)

Max Activating Token Index: 599

Text #5

Max Range: 1.4111. Min Range: -1.4111

Max Act: 0.9968. Min Act: -0.0000

Data Index: 1327418 (The Pile)

Max Activating Token Index: 276

Text #6

Max Range: 1.4111. Min Range: -1.4111

Max Act: 0.9156. Min Act: -0.0000

Data Index: 1708962 (The Pile)

Max Activating Token Index: 610

Text #7

Max Range: 1.4111. Min Range: -1.4111

Max Act: 0.9901. Min Act: -0.0000

Data Index: 1575157 (The Pile)

Max Activating Token Index: 164

Text #8

Max Range: 1.4111. Min Range: -1.4111

Max Act: 0.9608. Min Act: -0.0000

Data Index: 116763 (The Pile)

Max Activating Token Index: 850

Text #9

Max Range: 1.4111. Min Range: -1.4111

Max Act: 0.9675. Min Act: -0.0000

Data Index: 792110 (The Pile)

Max Activating Token Index: 1015

Text #10

Max Range: 1.4111. Min Range: -1.4111

Max Act: 0.9078. Min Act: -0.0000

Data Index: 1967517 (The Pile)

Max Activating Token Index: 927

Text #11

Max Range: 1.4111. Min Range: -1.4111

Max Act: 1.0259. Min Act: -0.0000

Data Index: 446593 (The Pile)

Max Activating Token Index: 784

Text #12

Max Range: 1.4111. Min Range: -1.4111

Max Act: 1.0196. Min Act: -0.0000

Data Index: 535351 (The Pile)

Max Activating Token Index: 869

Text #13

Max Range: 1.4111. Min Range: -1.4111

Max Act: 0.7639. Min Act: -0.0000

Data Index: 172637 (The Pile)

Max Activating Token Index: 983

Text #14

Max Range: 1.4111. Min Range: -1.4111

Max Act: 0.8926. Min Act: -0.0000

Data Index: 661520 (The Pile)

Max Activating Token Index: 587

Text #15

Max Range: 1.4111. Min Range: -1.4111

Max Act: 0.8664. Min Act: -0.0000

Data Index: 1147379 (The Pile)

Max Activating Token Index: 24

Text #16

Max Range: 1.4111. Min Range: -1.4111

Max Act: 0.8581. Min Act: -0.0000

Data Index: 1676197 (The Pile)

Max Activating Token Index: 27

Text #17

Max Range: 1.4111. Min Range: -1.4111

Max Act: 0.9183. Min Act: -0.0000

Data Index: 1380384 (The Pile)

Max Activating Token Index: 434

Text #18

Max Range: 1.4111. Min Range: -1.4111

Max Act: 0.8649. Min Act: -0.0000

Data Index: 450360 (The Pile)

Max Activating Token Index: 1009

Text #19

Max Range: 1.4111. Min Range: -1.4111

Max Act: 0.8611. Min Act: -0.0000

Data Index: 1945989 (The Pile)

Max Activating Token Index: 596