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

Dataset: The Pile

Neuron 2621 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5898. Min Range: -0.5898

Max Act: 0.5898. Min Act: -0.0000

Data Index: 1557314 (The Pile)

Max Activating Token Index: 639

Text #1

Max Range: 0.5898. Min Range: -0.5898

Max Act: 0.5547. Min Act: -0.0000

Data Index: 617727 (The Pile)

Max Activating Token Index: 748

Text #2

Max Range: 0.5898. Min Range: -0.5898

Max Act: 0.4511. Min Act: -0.0000

Data Index: 1591576 (The Pile)

Max Activating Token Index: 610

Text #3

Max Range: 0.5898. Min Range: -0.5898

Max Act: 0.4196. Min Act: -0.0000

Data Index: 676863 (The Pile)

Max Activating Token Index: 272

Text #4

Max Range: 0.5898. Min Range: -0.5898

Max Act: 0.4082. Min Act: -0.0000

Data Index: 1388528 (The Pile)

Max Activating Token Index: 11

Text #5

Max Range: 0.5898. Min Range: -0.5898

Max Act: 0.3774. Min Act: -0.0000

Data Index: 713917 (The Pile)

Max Activating Token Index: 703

Text #6

Max Range: 0.5898. Min Range: -0.5898

Max Act: 0.3448. Min Act: -0.0000

Data Index: 1989579 (The Pile)

Max Activating Token Index: 479

Text #7

Max Range: 0.5898. Min Range: -0.5898

Max Act: 0.3869. Min Act: -0.0000

Data Index: 456777 (The Pile)

Max Activating Token Index: 1000

Text #8

Max Range: 0.5898. Min Range: -0.5898

Max Act: 0.3383. Min Act: -0.0000

Data Index: 321288 (The Pile)

Max Activating Token Index: 930

Text #9

Max Range: 0.5898. Min Range: -0.5898

Max Act: 0.3703. Min Act: -0.0000

Data Index: 11108 (The Pile)

Max Activating Token Index: 277

Text #10

Max Range: 0.5898. Min Range: -0.5898

Max Act: 0.3620. Min Act: -0.0000

Data Index: 180847 (The Pile)

Max Activating Token Index: 383

Text #11

Max Range: 0.5898. Min Range: -0.5898

Max Act: 0.3534. Min Act: -0.0000

Data Index: 1046130 (The Pile)

Max Activating Token Index: 644

Text #12

Max Range: 0.5898. Min Range: -0.5898

Max Act: 0.3676. Min Act: -0.0000

Data Index: 1097811 (The Pile)

Max Activating Token Index: 898

Text #13

Max Range: 0.5898. Min Range: -0.5898

Max Act: 0.3426. Min Act: -0.0000

Data Index: 199732 (The Pile)

Max Activating Token Index: 223

Text #14

Max Range: 0.5898. Min Range: -0.5898

Max Act: 0.3373. Min Act: -0.0000

Data Index: 629514 (The Pile)

Max Activating Token Index: 1021

Text #15

Max Range: 0.5898. Min Range: -0.5898

Max Act: 0.3635. Min Act: -0.0000

Data Index: 1732252 (The Pile)

Max Activating Token Index: 297

Text #16

Max Range: 0.5898. Min Range: -0.5898

Max Act: 0.3639. Min Act: -0.0000

Data Index: 1288466 (The Pile)

Max Activating Token Index: 538

Text #17

Max Range: 0.5898. Min Range: -0.5898

Max Act: 0.3210. Min Act: -0.0000

Data Index: 1752675 (The Pile)

Max Activating Token Index: 708

Text #18

Max Range: 0.5898. Min Range: -0.5898

Max Act: 0.3201. Min Act: -0.0000

Data Index: 557934 (The Pile)

Max Activating Token Index: 299

Text #19

Max Range: 0.5898. Min Range: -0.5898

Max Act: 0.3194. Min Act: -0.0000

Data Index: 317654 (The Pile)

Max Activating Token Index: 704