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

Dataset: The Pile

Neuron 2035 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: 4.5983. Min Range: -4.5983

Max Act: 4.5421. Min Act: -0.0000

Data Index: 30768 (The Pile)

Max Activating Token Index: 596

Text #1

Max Range: 4.5983. Min Range: -4.5983

Max Act: 4.5983. Min Act: -0.0000

Data Index: 889197 (The Pile)

Max Activating Token Index: 558

Text #2

Max Range: 4.5983. Min Range: -4.5983

Max Act: 4.3983. Min Act: -0.0000

Data Index: 384575 (The Pile)

Max Activating Token Index: 328

Text #3

Max Range: 4.5983. Min Range: -4.5983

Max Act: 4.3404. Min Act: -0.0000

Data Index: 189046 (The Pile)

Max Activating Token Index: 63

Text #4

Max Range: 4.5983. Min Range: -4.5983

Max Act: 4.2295. Min Act: -0.0000

Data Index: 176517 (The Pile)

Max Activating Token Index: 324

Text #5

Max Range: 4.5983. Min Range: -4.5983

Max Act: 4.0400. Min Act: -0.0000

Data Index: 744574 (The Pile)

Max Activating Token Index: 686

Text #6

Max Range: 4.5983. Min Range: -4.5983

Max Act: 4.0204. Min Act: -0.0000

Data Index: 1320156 (The Pile)

Max Activating Token Index: 154

Text #7

Max Range: 4.5983. Min Range: -4.5983

Max Act: 3.8826. Min Act: -0.0000

Data Index: 1555157 (The Pile)

Max Activating Token Index: 559

Text #8

Max Range: 4.5983. Min Range: -4.5983

Max Act: 4.0147. Min Act: -0.0000

Data Index: 1817134 (The Pile)

Max Activating Token Index: 292

Text #9

Max Range: 4.5983. Min Range: -4.5983

Max Act: 3.9506. Min Act: -0.0000

Data Index: 1982006 (The Pile)

Max Activating Token Index: 35

Text #10

Max Range: 4.5983. Min Range: -4.5983

Max Act: 3.8690. Min Act: -0.0000

Data Index: 367631 (The Pile)

Max Activating Token Index: 45

Text #11

Max Range: 4.5983. Min Range: -4.5983

Max Act: 3.8253. Min Act: -0.0000

Data Index: 1880301 (The Pile)

Max Activating Token Index: 646

Text #12

Max Range: 4.5983. Min Range: -4.5983

Max Act: 3.6083. Min Act: -0.0000

Data Index: 1383244 (The Pile)

Max Activating Token Index: 996

Text #13

Max Range: 4.5983. Min Range: -4.5983

Max Act: 3.4352. Min Act: -0.0000

Data Index: 1723269 (The Pile)

Max Activating Token Index: 647

Text #14

Max Range: 4.5983. Min Range: -4.5983

Max Act: 3.6017. Min Act: -0.0000

Data Index: 379219 (The Pile)

Max Activating Token Index: 371

Text #15

Max Range: 4.5983. Min Range: -4.5983

Max Act: 4.0858. Min Act: -0.0000

Data Index: 898740 (The Pile)

Max Activating Token Index: 825

Text #16

Max Range: 4.5983. Min Range: -4.5983

Max Act: 3.8746. Min Act: -0.0000

Data Index: 326727 (The Pile)

Max Activating Token Index: 940

Text #17

Max Range: 4.5983. Min Range: -4.5983

Max Act: 3.7163. Min Act: -0.0000

Data Index: 1421397 (The Pile)

Max Activating Token Index: 819

Text #18

Max Range: 4.5983. Min Range: -4.5983

Max Act: 3.7025. Min Act: -0.0000

Data Index: 608202 (The Pile)

Max Activating Token Index: 352

Text #19

Max Range: 4.5983. Min Range: -4.5983

Max Act: 3.5786. Min Act: -0.0000

Data Index: 1171327 (The Pile)

Max Activating Token Index: 78