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

Dataset: The Pile

Neuron 1623 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4357. Min Range: -1.4357

Max Act: 1.4357. Min Act: -0.0000

Data Index: 1195613 (The Pile)

Max Activating Token Index: 623

Text #1

Max Range: 1.4357. Min Range: -1.4357

Max Act: 1.3880. Min Act: -0.0000

Data Index: 1345116 (The Pile)

Max Activating Token Index: 757

Text #2

Max Range: 1.4357. Min Range: -1.4357

Max Act: 1.2628. Min Act: -0.0000

Data Index: 1033058 (The Pile)

Max Activating Token Index: 145

Text #3

Max Range: 1.4357. Min Range: -1.4357

Max Act: 1.1688. Min Act: -0.0000

Data Index: 1676910 (The Pile)

Max Activating Token Index: 1011

Text #4

Max Range: 1.4357. Min Range: -1.4357

Max Act: 1.3049. Min Act: -0.0000

Data Index: 697366 (The Pile)

Max Activating Token Index: 179

Text #5

Max Range: 1.4357. Min Range: -1.4357

Max Act: 1.2433. Min Act: -0.0000

Data Index: 1689333 (The Pile)

Max Activating Token Index: 539

Text #6

Max Range: 1.4357. Min Range: -1.4357

Max Act: 1.1690. Min Act: -0.0000

Data Index: 371516 (The Pile)

Max Activating Token Index: 1009

Text #7

Max Range: 1.4357. Min Range: -1.4357

Max Act: 1.1529. Min Act: -0.0000

Data Index: 1912547 (The Pile)

Max Activating Token Index: 115

Text #8

Max Range: 1.4357. Min Range: -1.4357

Max Act: 1.1538. Min Act: -0.0000

Data Index: 208537 (The Pile)

Max Activating Token Index: 1012

Text #9

Max Range: 1.4357. Min Range: -1.4357

Max Act: 1.1188. Min Act: -0.0000

Data Index: 946670 (The Pile)

Max Activating Token Index: 196

Text #10

Max Range: 1.4357. Min Range: -1.4357

Max Act: 1.1526. Min Act: -0.0000

Data Index: 1501610 (The Pile)

Max Activating Token Index: 220

Text #11

Max Range: 1.4357. Min Range: -1.4357

Max Act: 1.1105. Min Act: -0.0000

Data Index: 1988679 (The Pile)

Max Activating Token Index: 946

Text #12

Max Range: 1.4357. Min Range: -1.4357

Max Act: 1.0560. Min Act: -0.0000

Data Index: 644659 (The Pile)

Max Activating Token Index: 46

Text #13

Max Range: 1.4357. Min Range: -1.4357

Max Act: 1.0896. Min Act: -0.0000

Data Index: 1184178 (The Pile)

Max Activating Token Index: 271

Text #14

Max Range: 1.4357. Min Range: -1.4357

Max Act: 1.0790. Min Act: -0.0000

Data Index: 1605609 (The Pile)

Max Activating Token Index: 757

Text #15

Max Range: 1.4357. Min Range: -1.4357

Max Act: 1.1521. Min Act: -0.0000

Data Index: 351951 (The Pile)

Max Activating Token Index: 749

Text #16

Max Range: 1.4357. Min Range: -1.4357

Max Act: 1.1197. Min Act: -0.0000

Data Index: 461676 (The Pile)

Max Activating Token Index: 361

Text #17

Max Range: 1.4357. Min Range: -1.4357

Max Act: 1.1161. Min Act: -0.0000

Data Index: 607020 (The Pile)

Max Activating Token Index: 587

Text #18

Max Range: 1.4357. Min Range: -1.4357

Max Act: 1.0220. Min Act: -0.0000

Data Index: 1079945 (The Pile)

Max Activating Token Index: 592

Text #19

Max Range: 1.4357. Min Range: -1.4357

Max Act: 0.9389. Min Act: -0.0000

Data Index: 1732606 (The Pile)

Max Activating Token Index: 517