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

Dataset: The Pile

Neuron 5070 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: 0.7543. Min Range: -0.7543

Max Act: 0.7543. Min Act: -0.0000

Data Index: 50659 (The Pile)

Max Activating Token Index: 513

Text #1

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.7525. Min Act: -0.0000

Data Index: 732278 (The Pile)

Max Activating Token Index: 506

Text #2

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.7189. Min Act: -0.0000

Data Index: 968573 (The Pile)

Max Activating Token Index: 78

Text #3

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.6986. Min Act: -0.0000

Data Index: 1019542 (The Pile)

Max Activating Token Index: 135

Text #4

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.6465. Min Act: -0.0000

Data Index: 362728 (The Pile)

Max Activating Token Index: 409

Text #5

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.6855. Min Act: -0.0000

Data Index: 1671906 (The Pile)

Max Activating Token Index: 93

Text #6

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.6329. Min Act: -0.0000

Data Index: 1728987 (The Pile)

Max Activating Token Index: 45

Text #7

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.6597. Min Act: -0.0000

Data Index: 172861 (The Pile)

Max Activating Token Index: 514

Text #8

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.6268. Min Act: -0.0000

Data Index: 1807133 (The Pile)

Max Activating Token Index: 255

Text #9

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.6028. Min Act: -0.0000

Data Index: 1324776 (The Pile)

Max Activating Token Index: 242

Text #10

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.6072. Min Act: -0.0000

Data Index: 532507 (The Pile)

Max Activating Token Index: 765

Text #11

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.5709. Min Act: -0.0000

Data Index: 732507 (The Pile)

Max Activating Token Index: 284

Text #12

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.6164. Min Act: -0.0000

Data Index: 791679 (The Pile)

Max Activating Token Index: 226

Text #13

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.5127. Min Act: -0.0000

Data Index: 47638 (The Pile)

Max Activating Token Index: 819

Text #14

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.5298. Min Act: -0.0000

Data Index: 283596 (The Pile)

Max Activating Token Index: 171

Text #15

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.5924. Min Act: -0.0000

Data Index: 923757 (The Pile)

Max Activating Token Index: 458

Text #16

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.5557. Min Act: -0.0000

Data Index: 576533 (The Pile)

Max Activating Token Index: 255

Text #17

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.5584. Min Act: -0.0000

Data Index: 1127515 (The Pile)

Max Activating Token Index: 480

Text #18

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.5601. Min Act: -0.0000

Data Index: 1177554 (The Pile)

Max Activating Token Index: 535

Text #19

Max Range: 0.7543. Min Range: -0.7543

Max Act: 0.5362. Min Act: -0.0000

Data Index: 641301 (The Pile)

Max Activating Token Index: 385