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

Dataset: The Pile

Neuron 70 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: 2.0038. Min Range: -2.0038

Max Act: 1.7796. Min Act: -0.0000

Data Index: 947443 (The Pile)

Max Activating Token Index: 245

Text #1

Max Range: 2.0038. Min Range: -2.0038

Max Act: 2.0038. Min Act: -0.0000

Data Index: 705697 (The Pile)

Max Activating Token Index: 748

Text #2

Max Range: 2.0038. Min Range: -2.0038

Max Act: 1.0485. Min Act: -0.0000

Data Index: 86018 (The Pile)

Max Activating Token Index: 597

Text #3

Max Range: 2.0038. Min Range: -2.0038

Max Act: 1.0557. Min Act: -0.0000

Data Index: 297789 (The Pile)

Max Activating Token Index: 146

Text #4

Max Range: 2.0038. Min Range: -2.0038

Max Act: 1.0148. Min Act: -0.0000

Data Index: 1251631 (The Pile)

Max Activating Token Index: 132

Text #5

Max Range: 2.0038. Min Range: -2.0038

Max Act: 0.9516. Min Act: -0.0000

Data Index: 1856670 (The Pile)

Max Activating Token Index: 454

Text #6

Max Range: 2.0038. Min Range: -2.0038

Max Act: 1.0555. Min Act: -0.0000

Data Index: 1654849 (The Pile)

Max Activating Token Index: 670

Text #7

Max Range: 2.0038. Min Range: -2.0038

Max Act: 0.9188. Min Act: -0.0000

Data Index: 1735799 (The Pile)

Max Activating Token Index: 417

Text #8

Max Range: 2.0038. Min Range: -2.0038

Max Act: 0.8225. Min Act: -0.0000

Data Index: 1988980 (The Pile)

Max Activating Token Index: 912

Text #9

Max Range: 2.0038. Min Range: -2.0038

Max Act: 0.8617. Min Act: -0.0000

Data Index: 562380 (The Pile)

Max Activating Token Index: 107

Text #10

Max Range: 2.0038. Min Range: -2.0038

Max Act: 0.6794. Min Act: -0.0000

Data Index: 790821 (The Pile)

Max Activating Token Index: 528

Text #11

Max Range: 2.0038. Min Range: -2.0038

Max Act: 0.7246. Min Act: -0.0000

Data Index: 110295 (The Pile)

Max Activating Token Index: 223

Text #12

Max Range: 2.0038. Min Range: -2.0038

Max Act: 0.7070. Min Act: -0.0000

Data Index: 1033499 (The Pile)

Max Activating Token Index: 111

Text #13

Max Range: 2.0038. Min Range: -2.0038

Max Act: 0.6570. Min Act: -0.0000

Data Index: 1110820 (The Pile)

Max Activating Token Index: 239

Text #14

Max Range: 2.0038. Min Range: -2.0038

Max Act: 0.6828. Min Act: -0.0000

Data Index: 848025 (The Pile)

Max Activating Token Index: 611

Text #15

Max Range: 2.0038. Min Range: -2.0038

Max Act: 0.7298. Min Act: -0.0000

Data Index: 785522 (The Pile)

Max Activating Token Index: 448

Text #16

Max Range: 2.0038. Min Range: -2.0038

Max Act: 0.6297. Min Act: -0.0000

Data Index: 1510553 (The Pile)

Max Activating Token Index: 83

Text #17

Max Range: 2.0038. Min Range: -2.0038

Max Act: 0.7071. Min Act: -0.0000

Data Index: 1704124 (The Pile)

Max Activating Token Index: 195

Text #18

Max Range: 2.0038. Min Range: -2.0038

Max Act: 0.6550. Min Act: 0.0000

Data Index: 340554 (The Pile)

Max Activating Token Index: 234

Text #19

Max Range: 2.0038. Min Range: -2.0038

Max Act: 0.6134. Min Act: 0.0000

Data Index: 1755967 (The Pile)

Max Activating Token Index: 703