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

Dataset: The Pile

Neuron 3407 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: 0.8041. Min Range: -0.8041

Max Act: 0.8041. Min Act: -0.0000

Data Index: 1075451 (The Pile)

Max Activating Token Index: 194

Text #1

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.7118. Min Act: -0.0000

Data Index: 944142 (The Pile)

Max Activating Token Index: 287

Text #2

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.6688. Min Act: -0.0000

Data Index: 326364 (The Pile)

Max Activating Token Index: 208

Text #3

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.6029. Min Act: 0.0000

Data Index: 944482 (The Pile)

Max Activating Token Index: 111

Text #4

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.5669. Min Act: -0.0000

Data Index: 508412 (The Pile)

Max Activating Token Index: 685

Text #5

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.6038. Min Act: -0.0000

Data Index: 267722 (The Pile)

Max Activating Token Index: 471

Text #6

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.5579. Min Act: -0.0000

Data Index: 866447 (The Pile)

Max Activating Token Index: 433

Text #7

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.5503. Min Act: -0.0000

Data Index: 968451 (The Pile)

Max Activating Token Index: 1006

Text #8

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.5521. Min Act: -0.0000

Data Index: 1115359 (The Pile)

Max Activating Token Index: 763

Text #9

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.5527. Min Act: -0.0000

Data Index: 1847854 (The Pile)

Max Activating Token Index: 43

Text #10

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.5783. Min Act: -0.0000

Data Index: 1037800 (The Pile)

Max Activating Token Index: 939

Text #11

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.5304. Min Act: -0.0000

Data Index: 595196 (The Pile)

Max Activating Token Index: 1012

Text #12

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.5735. Min Act: -0.0000

Data Index: 287469 (The Pile)

Max Activating Token Index: 713

Text #13

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.5520. Min Act: -0.0000

Data Index: 1956986 (The Pile)

Max Activating Token Index: 783

Text #14

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.5311. Min Act: -0.0000

Data Index: 639409 (The Pile)

Max Activating Token Index: 263

Text #15

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.5018. Min Act: -0.0000

Data Index: 1649308 (The Pile)

Max Activating Token Index: 190

Text #16

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.5352. Min Act: -0.0000

Data Index: 482641 (The Pile)

Max Activating Token Index: 416

Text #17

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.5137. Min Act: -0.0000

Data Index: 1070527 (The Pile)

Max Activating Token Index: 919

Text #18

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.5558. Min Act: -0.0000

Data Index: 1717140 (The Pile)

Max Activating Token Index: 561

Text #19

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.5449. Min Act: -0.0000

Data Index: 1709589 (The Pile)

Max Activating Token Index: 816