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

Dataset: The Pile

Neuron 4226 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.6131. Min Act: -0.0000

Data Index: 457967 (The Pile)

Max Activating Token Index: 320

Text #1

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.4917. Min Act: -0.0000

Data Index: 1818163 (The Pile)

Max Activating Token Index: 481

Text #2

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.5099. Min Act: -0.0000

Data Index: 699006 (The Pile)

Max Activating Token Index: 423

Text #3

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.4511. Min Act: -0.0000

Data Index: 39651 (The Pile)

Max Activating Token Index: 235

Text #4

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.5244. Min Act: -0.0000

Data Index: 540731 (The Pile)

Max Activating Token Index: 887

Text #5

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.4261. Min Act: -0.0000

Data Index: 688222 (The Pile)

Max Activating Token Index: 112

Text #6

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.4475. Min Act: -0.0000

Data Index: 865787 (The Pile)

Max Activating Token Index: 442

Text #7

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.4589. Min Act: -0.0000

Data Index: 1066773 (The Pile)

Max Activating Token Index: 355

Text #8

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.4682. Min Act: -0.0000

Data Index: 1217574 (The Pile)

Max Activating Token Index: 722

Text #9

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.3829. Min Act: -0.0000

Data Index: 375729 (The Pile)

Max Activating Token Index: 935

Text #10

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.4500. Min Act: -0.0000

Data Index: 1910459 (The Pile)

Max Activating Token Index: 587

Text #11

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.4059. Min Act: -0.0000

Data Index: 825479 (The Pile)

Max Activating Token Index: 513

Text #12

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.4172. Min Act: -0.0000

Data Index: 94768 (The Pile)

Max Activating Token Index: 519

Text #13

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.4032. Min Act: -0.0000

Data Index: 1375977 (The Pile)

Max Activating Token Index: 346

Text #14

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.3584. Min Act: -0.0000

Data Index: 1559564 (The Pile)

Max Activating Token Index: 54

Text #15

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.3899. Min Act: -0.0000

Data Index: 1878695 (The Pile)

Max Activating Token Index: 359

Text #16

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.3844. Min Act: -0.0000

Data Index: 492931 (The Pile)

Max Activating Token Index: 885

Text #17

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.4137. Min Act: -0.0000

Data Index: 999784 (The Pile)

Max Activating Token Index: 250

Text #18

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.3704. Min Act: -0.0000

Data Index: 243416 (The Pile)

Max Activating Token Index: 1016

Text #19

Max Range: 0.6131. Min Range: -0.6131

Max Act: 0.3710. Min Act: -0.0000

Data Index: 1751404 (The Pile)

Max Activating Token Index: 312