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

Dataset: The Pile

Neuron 1227 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.4261. Min Act: -0.0000

Data Index: 611792 (The Pile)

Max Activating Token Index: 110

Text #1

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.4152. Min Act: -0.0000

Data Index: 139025 (The Pile)

Max Activating Token Index: 94

Text #2

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.3596. Min Act: -0.0000

Data Index: 1583123 (The Pile)

Max Activating Token Index: 592

Text #3

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.4391. Min Act: -0.0000

Data Index: 594741 (The Pile)

Max Activating Token Index: 775

Text #4

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.3346. Min Act: -0.0000

Data Index: 1033585 (The Pile)

Max Activating Token Index: 739

Text #5

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.3291. Min Act: -0.0000

Data Index: 985281 (The Pile)

Max Activating Token Index: 797

Text #6

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.3902. Min Act: -0.0000

Data Index: 494131 (The Pile)

Max Activating Token Index: 725

Text #7

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.3310. Min Act: -0.0000

Data Index: 461652 (The Pile)

Max Activating Token Index: 335

Text #8

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.3427. Min Act: -0.0000

Data Index: 375025 (The Pile)

Max Activating Token Index: 993

Text #9

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.3030. Min Act: -0.0000

Data Index: 1219122 (The Pile)

Max Activating Token Index: 131

Text #10

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.3097. Min Act: -0.0000

Data Index: 1621701 (The Pile)

Max Activating Token Index: 877

Text #11

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.3288. Min Act: -0.0000

Data Index: 1433724 (The Pile)

Max Activating Token Index: 768

Text #12

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.3030. Min Act: -0.0000

Data Index: 699146 (The Pile)

Max Activating Token Index: 340

Text #13

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.3020. Min Act: -0.0000

Data Index: 1683386 (The Pile)

Max Activating Token Index: 147

Text #14

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.2666. Min Act: -0.0000

Data Index: 444284 (The Pile)

Max Activating Token Index: 934

Text #15

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.3015. Min Act: -0.0000

Data Index: 781632 (The Pile)

Max Activating Token Index: 943

Text #16

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.2828. Min Act: -0.0000

Data Index: 1697792 (The Pile)

Max Activating Token Index: 417

Text #17

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.2690. Min Act: -0.0000

Data Index: 1387645 (The Pile)

Max Activating Token Index: 761

Text #18

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.2780. Min Act: -0.0000

Data Index: 748716 (The Pile)

Max Activating Token Index: 479

Text #19

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.2762. Min Act: -0.0000

Data Index: 1990387 (The Pile)

Max Activating Token Index: 117