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

Dataset: The Pile

Neuron 4005 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.6350. Min Act: -0.0000

Data Index: 1039883 (The Pile)

Max Activating Token Index: 615

Text #1

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.6723. Min Act: -0.0000

Data Index: 1399856 (The Pile)

Max Activating Token Index: 958

Text #2

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.6707. Min Act: -0.0000

Data Index: 286346 (The Pile)

Max Activating Token Index: 521

Text #3

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.6382. Min Act: -0.0000

Data Index: 1923534 (The Pile)

Max Activating Token Index: 99

Text #4

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.6448. Min Act: -0.0000

Data Index: 540458 (The Pile)

Max Activating Token Index: 247

Text #5

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5358. Min Act: -0.0000

Data Index: 1693271 (The Pile)

Max Activating Token Index: 132

Text #6

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5189. Min Act: -0.0000

Data Index: 745594 (The Pile)

Max Activating Token Index: 88

Text #7

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5460. Min Act: -0.0000

Data Index: 689479 (The Pile)

Max Activating Token Index: 430

Text #8

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5552. Min Act: -0.0000

Data Index: 333696 (The Pile)

Max Activating Token Index: 285

Text #9

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5774. Min Act: -0.0000

Data Index: 274359 (The Pile)

Max Activating Token Index: 561

Text #10

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5230. Min Act: -0.0000

Data Index: 1452829 (The Pile)

Max Activating Token Index: 452

Text #11

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5619. Min Act: -0.0000

Data Index: 1522389 (The Pile)

Max Activating Token Index: 1009

Text #12

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.6172. Min Act: -0.0000

Data Index: 619874 (The Pile)

Max Activating Token Index: 237

Text #13

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5715. Min Act: -0.0000

Data Index: 1813624 (The Pile)

Max Activating Token Index: 13

Text #14

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4786. Min Act: -0.0000

Data Index: 1698351 (The Pile)

Max Activating Token Index: 990

Text #15

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4688. Min Act: -0.0000

Data Index: 370346 (The Pile)

Max Activating Token Index: 778

Text #16

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5634. Min Act: -0.0000

Data Index: 1073053 (The Pile)

Max Activating Token Index: 115

Text #17

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4586. Min Act: -0.0000

Data Index: 707768 (The Pile)

Max Activating Token Index: 151

Text #18

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4965. Min Act: -0.0000

Data Index: 987437 (The Pile)

Max Activating Token Index: 277

Text #19

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5085. Min Act: -0.0000

Data Index: 713258 (The Pile)

Max Activating Token Index: 426