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

Dataset: The Pile

Neuron 2840 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: 0.5329. Min Range: -0.5329

Max Act: 0.5329. Min Act: -0.0000

Data Index: 751122 (The Pile)

Max Activating Token Index: 500

Text #1

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4645. Min Act: -0.0000

Data Index: 1057629 (The Pile)

Max Activating Token Index: 254

Text #2

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4592. Min Act: -0.0000

Data Index: 1772483 (The Pile)

Max Activating Token Index: 355

Text #3

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4204. Min Act: -0.0000

Data Index: 1694671 (The Pile)

Max Activating Token Index: 178

Text #4

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4079. Min Act: -0.0000

Data Index: 312911 (The Pile)

Max Activating Token Index: 957

Text #5

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.3768. Min Act: -0.0000

Data Index: 1365770 (The Pile)

Max Activating Token Index: 188

Text #6

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.3707. Min Act: -0.0000

Data Index: 481441 (The Pile)

Max Activating Token Index: 103

Text #7

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.3774. Min Act: -0.0000

Data Index: 1229700 (The Pile)

Max Activating Token Index: 935

Text #8

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.3381. Min Act: -0.0000

Data Index: 555122 (The Pile)

Max Activating Token Index: 647

Text #9

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.3156. Min Act: -0.0000

Data Index: 808097 (The Pile)

Max Activating Token Index: 728

Text #10

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.3338. Min Act: -0.0000

Data Index: 1285572 (The Pile)

Max Activating Token Index: 919

Text #11

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.3491. Min Act: -0.0000

Data Index: 500416 (The Pile)

Max Activating Token Index: 46

Text #12

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.3200. Min Act: -0.0000

Data Index: 221081 (The Pile)

Max Activating Token Index: 220

Text #13

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.3352. Min Act: -0.0000

Data Index: 625289 (The Pile)

Max Activating Token Index: 477

Text #14

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.3131. Min Act: -0.0000

Data Index: 336208 (The Pile)

Max Activating Token Index: 182

Text #15

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.3442. Min Act: 0.0000

Data Index: 542970 (The Pile)

Max Activating Token Index: 675

Text #16

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.3232. Min Act: 0.0000

Data Index: 1660511 (The Pile)

Max Activating Token Index: 491

Text #17

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.3311. Min Act: -0.0000

Data Index: 281504 (The Pile)

Max Activating Token Index: 570

Text #18

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.3539. Min Act: -0.0000

Data Index: 1215006 (The Pile)

Max Activating Token Index: 672

Text #19

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.3318. Min Act: 0.0000

Data Index: 901086 (The Pile)

Max Activating Token Index: 911