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

Dataset: The Pile

Neuron 2902 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: 3.4163. Min Range: -3.4163

Max Act: 3.4140. Min Act: -0.0000

Data Index: 543760 (The Pile)

Max Activating Token Index: 393

Text #1

Max Range: 3.4163. Min Range: -3.4163

Max Act: 3.4163. Min Act: -0.0000

Data Index: 1817213 (The Pile)

Max Activating Token Index: 896

Text #2

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.6476. Min Act: -0.0000

Data Index: 1616524 (The Pile)

Max Activating Token Index: 427

Text #3

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.7366. Min Act: -0.0000

Data Index: 1171325 (The Pile)

Max Activating Token Index: 762

Text #4

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.5208. Min Act: -0.0000

Data Index: 685868 (The Pile)

Max Activating Token Index: 21

Text #5

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.4406. Min Act: -0.0000

Data Index: 80976 (The Pile)

Max Activating Token Index: 764

Text #6

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.2077. Min Act: -0.0000

Data Index: 135138 (The Pile)

Max Activating Token Index: 1012

Text #7

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.4447. Min Act: -0.0000

Data Index: 10496 (The Pile)

Max Activating Token Index: 656

Text #8

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.2881. Min Act: -0.0000

Data Index: 1434086 (The Pile)

Max Activating Token Index: 528

Text #9

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.2438. Min Act: -0.0000

Data Index: 1741657 (The Pile)

Max Activating Token Index: 960

Text #10

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.2220. Min Act: -0.0000

Data Index: 1542445 (The Pile)

Max Activating Token Index: 934

Text #11

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.0825. Min Act: -0.0000

Data Index: 1537113 (The Pile)

Max Activating Token Index: 927

Text #12

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.2122. Min Act: -0.0000

Data Index: 1567126 (The Pile)

Max Activating Token Index: 156

Text #13

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.0867. Min Act: -0.0000

Data Index: 883635 (The Pile)

Max Activating Token Index: 282

Text #14

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.3117. Min Act: -0.0000

Data Index: 344292 (The Pile)

Max Activating Token Index: 313

Text #15

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.1644. Min Act: -0.0000

Data Index: 272805 (The Pile)

Max Activating Token Index: 324

Text #16

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.1517. Min Act: -0.0000

Data Index: 832760 (The Pile)

Max Activating Token Index: 974

Text #17

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.0470. Min Act: -0.0000

Data Index: 146252 (The Pile)

Max Activating Token Index: 108

Text #18

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.2648. Min Act: -0.0000

Data Index: 1593493 (The Pile)

Max Activating Token Index: 392

Text #19

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.2674. Min Act: -0.0000

Data Index: 1307330 (The Pile)

Max Activating Token Index: 700