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

Dataset: The Pile

Neuron 2617 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: 1.0251. Min Range: -1.0251

Max Act: 1.0251. Min Act: -0.0000

Data Index: 206432 (The Pile)

Max Activating Token Index: 596

Text #1

Max Range: 1.0251. Min Range: -1.0251

Max Act: 0.9087. Min Act: -0.0000

Data Index: 1608414 (The Pile)

Max Activating Token Index: 764

Text #2

Max Range: 1.0251. Min Range: -1.0251

Max Act: 0.7708. Min Act: -0.0000

Data Index: 659464 (The Pile)

Max Activating Token Index: 367

Text #3

Max Range: 1.0251. Min Range: -1.0251

Max Act: 0.7810. Min Act: -0.0000

Data Index: 261963 (The Pile)

Max Activating Token Index: 198

Text #4

Max Range: 1.0251. Min Range: -1.0251

Max Act: 0.7790. Min Act: -0.0000

Data Index: 1660212 (The Pile)

Max Activating Token Index: 183

Text #5

Max Range: 1.0251. Min Range: -1.0251

Max Act: 0.6721. Min Act: -0.0000

Data Index: 1682235 (The Pile)

Max Activating Token Index: 1021

Text #6

Max Range: 1.0251. Min Range: -1.0251

Max Act: 0.7423. Min Act: -0.0000

Data Index: 956676 (The Pile)

Max Activating Token Index: 194

Text #7

Max Range: 1.0251. Min Range: -1.0251

Max Act: 0.7007. Min Act: -0.0000

Data Index: 747335 (The Pile)

Max Activating Token Index: 98

Text #8

Max Range: 1.0251. Min Range: -1.0251

Max Act: 0.6803. Min Act: -0.0000

Data Index: 90583 (The Pile)

Max Activating Token Index: 293

Text #9

Max Range: 1.0251. Min Range: -1.0251

Max Act: 0.6856. Min Act: -0.0000

Data Index: 1688658 (The Pile)

Max Activating Token Index: 224

Text #10

Max Range: 1.0251. Min Range: -1.0251

Max Act: 0.6516. Min Act: -0.0000

Data Index: 353291 (The Pile)

Max Activating Token Index: 183

Text #11

Max Range: 1.0251. Min Range: -1.0251

Max Act: 0.6609. Min Act: -0.0000

Data Index: 1284346 (The Pile)

Max Activating Token Index: 696

Text #12

Max Range: 1.0251. Min Range: -1.0251

Max Act: 0.6347. Min Act: -0.0000

Data Index: 1780104 (The Pile)

Max Activating Token Index: 928

Text #13

Max Range: 1.0251. Min Range: -1.0251

Max Act: 0.7582. Min Act: -0.0000

Data Index: 389170 (The Pile)

Max Activating Token Index: 838

Text #14

Max Range: 1.0251. Min Range: -1.0251

Max Act: 0.6414. Min Act: -0.0000

Data Index: 1030076 (The Pile)

Max Activating Token Index: 278

Text #15

Max Range: 1.0251. Min Range: -1.0251

Max Act: 0.6278. Min Act: -0.0000

Data Index: 674767 (The Pile)

Max Activating Token Index: 733

Text #16

Max Range: 1.0251. Min Range: -1.0251

Max Act: 0.5723. Min Act: -0.0000

Data Index: 38571 (The Pile)

Max Activating Token Index: 179

Text #17

Max Range: 1.0251. Min Range: -1.0251

Max Act: 0.5838. Min Act: -0.0000

Data Index: 30642 (The Pile)

Max Activating Token Index: 33

Text #18

Max Range: 1.0251. Min Range: -1.0251

Max Act: 0.6108. Min Act: -0.0000

Data Index: 1466039 (The Pile)

Max Activating Token Index: 596

Text #19

Max Range: 1.0251. Min Range: -1.0251

Max Act: 0.6271. Min Act: -0.0000

Data Index: 1891390 (The Pile)

Max Activating Token Index: 477