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

Dataset: The Pile

Neuron 59 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6251. Min Range: -3.6251

Max Act: 3.6251. Min Act: -0.0000

Data Index: 1659283 (The Pile)

Max Activating Token Index: 305

Text #1

Max Range: 3.6251. Min Range: -3.6251

Max Act: 3.4135. Min Act: -0.0000

Data Index: 279577 (The Pile)

Max Activating Token Index: 448

Text #2

Max Range: 3.6251. Min Range: -3.6251

Max Act: 3.2057. Min Act: -0.0000

Data Index: 1958071 (The Pile)

Max Activating Token Index: 97

Text #3

Max Range: 3.6251. Min Range: -3.6251

Max Act: 3.1815. Min Act: -0.0000

Data Index: 1614431 (The Pile)

Max Activating Token Index: 215

Text #4

Max Range: 3.6251. Min Range: -3.6251

Max Act: 3.0437. Min Act: -0.0000

Data Index: 1164925 (The Pile)

Max Activating Token Index: 517

Text #5

Max Range: 3.6251. Min Range: -3.6251

Max Act: 3.0120. Min Act: -0.0000

Data Index: 1986977 (The Pile)

Max Activating Token Index: 496

Text #6

Max Range: 3.6251. Min Range: -3.6251

Max Act: 3.0614. Min Act: -0.0000

Data Index: 1719612 (The Pile)

Max Activating Token Index: 101

Text #7

Max Range: 3.6251. Min Range: -3.6251

Max Act: 2.8744. Min Act: -0.0000

Data Index: 752598 (The Pile)

Max Activating Token Index: 664

Text #8

Max Range: 3.6251. Min Range: -3.6251

Max Act: 3.2948. Min Act: -0.0000

Data Index: 624389 (The Pile)

Max Activating Token Index: 135

Text #9

Max Range: 3.6251. Min Range: -3.6251

Max Act: 3.1294. Min Act: -0.0000

Data Index: 1999239 (The Pile)

Max Activating Token Index: 480

Text #10

Max Range: 3.6251. Min Range: -3.6251

Max Act: 2.9635. Min Act: -0.0000

Data Index: 1355049 (The Pile)

Max Activating Token Index: 243

Text #11

Max Range: 3.6251. Min Range: -3.6251

Max Act: 3.1014. Min Act: -0.0000

Data Index: 1316693 (The Pile)

Max Activating Token Index: 291

Text #12

Max Range: 3.6251. Min Range: -3.6251

Max Act: 3.0906. Min Act: -0.0000

Data Index: 1336854 (The Pile)

Max Activating Token Index: 471

Text #13

Max Range: 3.6251. Min Range: -3.6251

Max Act: 2.9438. Min Act: -0.0000

Data Index: 543458 (The Pile)

Max Activating Token Index: 130

Text #14

Max Range: 3.6251. Min Range: -3.6251

Max Act: 2.9614. Min Act: -0.0000

Data Index: 1698592 (The Pile)

Max Activating Token Index: 535

Text #15

Max Range: 3.6251. Min Range: -3.6251

Max Act: 3.0862. Min Act: -0.0000

Data Index: 318197 (The Pile)

Max Activating Token Index: 90

Text #16

Max Range: 3.6251. Min Range: -3.6251

Max Act: 2.7437. Min Act: -0.0000

Data Index: 294882 (The Pile)

Max Activating Token Index: 499

Text #17

Max Range: 3.6251. Min Range: -3.6251

Max Act: 3.0116. Min Act: -0.0000

Data Index: 179309 (The Pile)

Max Activating Token Index: 721

Text #18

Max Range: 3.6251. Min Range: -3.6251

Max Act: 3.0068. Min Act: -0.0000

Data Index: 478207 (The Pile)

Max Activating Token Index: 632

Text #19

Max Range: 3.6251. Min Range: -3.6251

Max Act: 3.0048. Min Act: -0.0000

Data Index: 1212994 (The Pile)

Max Activating Token Index: 119