Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 792 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.8132. Min Act: -0.0000

Data Index: 767434 (The Pile)

Max Activating Token Index: 879

Text #1

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.7400. Min Act: -0.0000

Data Index: 1259675 (The Pile)

Max Activating Token Index: 167

Text #2

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.8254. Min Act: -0.0000

Data Index: 554285 (The Pile)

Max Activating Token Index: 274

Text #3

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.7374. Min Act: -0.0000

Data Index: 1551886 (The Pile)

Max Activating Token Index: 452

Text #4

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.7883. Min Act: -0.0000

Data Index: 147295 (The Pile)

Max Activating Token Index: 85

Text #5

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.7978. Min Act: -0.0000

Data Index: 964615 (The Pile)

Max Activating Token Index: 1003

Text #6

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.7157. Min Act: -0.0000

Data Index: 1444624 (The Pile)

Max Activating Token Index: 736

Text #7

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.6441. Min Act: 0.0000

Data Index: 1988865 (The Pile)

Max Activating Token Index: 523

Text #8

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.6323. Min Act: -0.0000

Data Index: 1149062 (The Pile)

Max Activating Token Index: 780

Text #9

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.6707. Min Act: -0.0000

Data Index: 754997 (The Pile)

Max Activating Token Index: 971

Text #10

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.6664. Min Act: -0.0000

Data Index: 332299 (The Pile)

Max Activating Token Index: 430

Text #11

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.6627. Min Act: -0.0000

Data Index: 1056385 (The Pile)

Max Activating Token Index: 866

Text #12

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.6829. Min Act: -0.0000

Data Index: 1481712 (The Pile)

Max Activating Token Index: 123

Text #13

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.6382. Min Act: -0.0000

Data Index: 310495 (The Pile)

Max Activating Token Index: 416

Text #14

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.6752. Min Act: -0.0000

Data Index: 63574 (The Pile)

Max Activating Token Index: 962

Text #15

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.7001. Min Act: -0.0000

Data Index: 1778576 (The Pile)

Max Activating Token Index: 755

Text #16

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.6758. Min Act: -0.0000

Data Index: 861244 (The Pile)

Max Activating Token Index: 259

Text #17

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.6520. Min Act: 0.0000

Data Index: 1188958 (The Pile)

Max Activating Token Index: 693

Text #18

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.6606. Min Act: 0.0000

Data Index: 1289387 (The Pile)

Max Activating Token Index: 302

Text #19

Max Range: 0.8254. Min Range: -0.8254

Max Act: 0.6200. Min Act: -0.0000

Data Index: 1111636 (The Pile)

Max Activating Token Index: 484