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

Dataset: The Pile

Neuron 447 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.7810. Min Act: -0.0000

Data Index: 1158650 (The Pile)

Max Activating Token Index: 924

Text #1

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.7625. Min Act: -0.0000

Data Index: 1619249 (The Pile)

Max Activating Token Index: 379

Text #2

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.7195. Min Act: -0.0000

Data Index: 1171950 (The Pile)

Max Activating Token Index: 977

Text #3

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.7204. Min Act: -0.0000

Data Index: 1369564 (The Pile)

Max Activating Token Index: 352

Text #4

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.7369. Min Act: -0.0000

Data Index: 502626 (The Pile)

Max Activating Token Index: 80

Text #5

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6976. Min Act: -0.0000

Data Index: 1515727 (The Pile)

Max Activating Token Index: 607

Text #6

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6875. Min Act: -0.0000

Data Index: 1751524 (The Pile)

Max Activating Token Index: 798

Text #7

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6531. Min Act: -0.0000

Data Index: 824724 (The Pile)

Max Activating Token Index: 331

Text #8

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.5991. Min Act: -0.0000

Data Index: 1785600 (The Pile)

Max Activating Token Index: 623

Text #9

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6862. Min Act: -0.0000

Data Index: 921536 (The Pile)

Max Activating Token Index: 248

Text #10

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.5570. Min Act: -0.0000

Data Index: 1165963 (The Pile)

Max Activating Token Index: 827

Text #11

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6173. Min Act: -0.0000

Data Index: 756980 (The Pile)

Max Activating Token Index: 696

Text #12

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.7136. Min Act: -0.0000

Data Index: 770967 (The Pile)

Max Activating Token Index: 923

Text #13

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6834. Min Act: -0.0000

Data Index: 1880084 (The Pile)

Max Activating Token Index: 531

Text #14

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6102. Min Act: -0.0000

Data Index: 973509 (The Pile)

Max Activating Token Index: 427

Text #15

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.5733. Min Act: -0.0000

Data Index: 1135615 (The Pile)

Max Activating Token Index: 876

Text #16

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.5545. Min Act: -0.0000

Data Index: 1757333 (The Pile)

Max Activating Token Index: 258

Text #17

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6313. Min Act: -0.0000

Data Index: 1662507 (The Pile)

Max Activating Token Index: 57

Text #18

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.5954. Min Act: -0.0000

Data Index: 1193941 (The Pile)

Max Activating Token Index: 983

Text #19

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.5271. Min Act: -0.0000

Data Index: 589841 (The Pile)

Max Activating Token Index: 966