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

Dataset: The Pile

Neuron 3574 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.4067. Min Act: -0.0000

Data Index: 307919 (The Pile)

Max Activating Token Index: 59

Text #1

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.4026. Min Act: -0.0000

Data Index: 629081 (The Pile)

Max Activating Token Index: 395

Text #2

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.3797. Min Act: -0.0000

Data Index: 1332943 (The Pile)

Max Activating Token Index: 446

Text #3

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.3578. Min Act: -0.0000

Data Index: 1354055 (The Pile)

Max Activating Token Index: 957

Text #4

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.3530. Min Act: -0.0000

Data Index: 517063 (The Pile)

Max Activating Token Index: 979

Text #5

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.3582. Min Act: -0.0000

Data Index: 719954 (The Pile)

Max Activating Token Index: 904

Text #6

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.3512. Min Act: -0.0000

Data Index: 1130703 (The Pile)

Max Activating Token Index: 521

Text #7

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.3499. Min Act: -0.0000

Data Index: 180690 (The Pile)

Max Activating Token Index: 677

Text #8

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.3458. Min Act: -0.0000

Data Index: 1337205 (The Pile)

Max Activating Token Index: 843

Text #9

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.3254. Min Act: -0.0000

Data Index: 1561648 (The Pile)

Max Activating Token Index: 383

Text #10

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.3225. Min Act: -0.0000

Data Index: 730440 (The Pile)

Max Activating Token Index: 598

Text #11

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.3418. Min Act: -0.0000

Data Index: 1380635 (The Pile)

Max Activating Token Index: 652

Text #12

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.3090. Min Act: -0.0000

Data Index: 327903 (The Pile)

Max Activating Token Index: 319

Text #13

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.2941. Min Act: -0.0000

Data Index: 702441 (The Pile)

Max Activating Token Index: 219

Text #14

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.2820. Min Act: -0.0000

Data Index: 754324 (The Pile)

Max Activating Token Index: 859

Text #15

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.3076. Min Act: -0.0000

Data Index: 1354676 (The Pile)

Max Activating Token Index: 1014

Text #16

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.2889. Min Act: -0.0000

Data Index: 1432062 (The Pile)

Max Activating Token Index: 269

Text #17

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.3404. Min Act: -0.0000

Data Index: 1493520 (The Pile)

Max Activating Token Index: 321

Text #18

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.3078. Min Act: -0.0000

Data Index: 1601025 (The Pile)

Max Activating Token Index: 281

Text #19

Max Range: 0.4067. Min Range: -0.4067

Max Act: 0.3053. Min Act: -0.0000

Data Index: 672007 (The Pile)

Max Activating Token Index: 202