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

Dataset: The Pile

Neuron 4204 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: 1.1484. Min Range: -1.1484

Max Act: 1.1484. Min Act: -0.0000

Data Index: 1627258 (The Pile)

Max Activating Token Index: 86

Text #1

Max Range: 1.1484. Min Range: -1.1484

Max Act: 1.0499. Min Act: -0.0000

Data Index: 847328 (The Pile)

Max Activating Token Index: 1021

Text #2

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.8714. Min Act: -0.0000

Data Index: 1332345 (The Pile)

Max Activating Token Index: 614

Text #3

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.8472. Min Act: -0.0000

Data Index: 846140 (The Pile)

Max Activating Token Index: 291

Text #4

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.8196. Min Act: -0.0000

Data Index: 445653 (The Pile)

Max Activating Token Index: 756

Text #5

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.7250. Min Act: -0.0000

Data Index: 714390 (The Pile)

Max Activating Token Index: 590

Text #6

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.7959. Min Act: -0.0000

Data Index: 894039 (The Pile)

Max Activating Token Index: 775

Text #7

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.7463. Min Act: -0.0000

Data Index: 1063927 (The Pile)

Max Activating Token Index: 428

Text #8

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.6941. Min Act: -0.0000

Data Index: 997197 (The Pile)

Max Activating Token Index: 68

Text #9

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.7815. Min Act: -0.0000

Data Index: 1077184 (The Pile)

Max Activating Token Index: 839

Text #10

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.7394. Min Act: -0.0000

Data Index: 393753 (The Pile)

Max Activating Token Index: 171

Text #11

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.6954. Min Act: -0.0000

Data Index: 1917317 (The Pile)

Max Activating Token Index: 1020

Text #12

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.6934. Min Act: -0.0000

Data Index: 48081 (The Pile)

Max Activating Token Index: 143

Text #13

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.6521. Min Act: -0.0000

Data Index: 421820 (The Pile)

Max Activating Token Index: 653

Text #14

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.6869. Min Act: -0.0000

Data Index: 973727 (The Pile)

Max Activating Token Index: 94

Text #15

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.6633. Min Act: -0.0000

Data Index: 1945461 (The Pile)

Max Activating Token Index: 248

Text #16

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.7163. Min Act: -0.0000

Data Index: 194869 (The Pile)

Max Activating Token Index: 720

Text #17

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.6608. Min Act: -0.0000

Data Index: 242850 (The Pile)

Max Activating Token Index: 207

Text #18

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.6195. Min Act: -0.0000

Data Index: 1026429 (The Pile)

Max Activating Token Index: 873

Text #19

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.6559. Min Act: -0.0000

Data Index: 1449397 (The Pile)

Max Activating Token Index: 518