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

Dataset: The Pile

Neuron 3669 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: 0.5259. Min Range: -0.5259

Max Act: 0.5259. Min Act: -0.0000

Data Index: 1406074 (The Pile)

Max Activating Token Index: 916

Text #1

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.5217. Min Act: -0.0000

Data Index: 1588085 (The Pile)

Max Activating Token Index: 787

Text #2

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4873. Min Act: -0.0000

Data Index: 1729716 (The Pile)

Max Activating Token Index: 70

Text #3

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4872. Min Act: -0.0000

Data Index: 1320536 (The Pile)

Max Activating Token Index: 958

Text #4

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4476. Min Act: -0.0000

Data Index: 1209715 (The Pile)

Max Activating Token Index: 310

Text #5

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.3962. Min Act: -0.0000

Data Index: 540916 (The Pile)

Max Activating Token Index: 86

Text #6

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4528. Min Act: -0.0000

Data Index: 509088 (The Pile)

Max Activating Token Index: 723

Text #7

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4264. Min Act: -0.0000

Data Index: 324369 (The Pile)

Max Activating Token Index: 803

Text #8

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4118. Min Act: -0.0000

Data Index: 491091 (The Pile)

Max Activating Token Index: 272

Text #9

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4678. Min Act: -0.0000

Data Index: 1057485 (The Pile)

Max Activating Token Index: 520

Text #10

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4322. Min Act: -0.0000

Data Index: 779700 (The Pile)

Max Activating Token Index: 177

Text #11

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4210. Min Act: -0.0000

Data Index: 581963 (The Pile)

Max Activating Token Index: 733

Text #12

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.3705. Min Act: -0.0000

Data Index: 840198 (The Pile)

Max Activating Token Index: 762

Text #13

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4176. Min Act: -0.0000

Data Index: 911723 (The Pile)

Max Activating Token Index: 435

Text #14

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4313. Min Act: -0.0000

Data Index: 1689213 (The Pile)

Max Activating Token Index: 901

Text #15

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.3991. Min Act: -0.0000

Data Index: 1345573 (The Pile)

Max Activating Token Index: 534

Text #16

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.3961. Min Act: -0.0000

Data Index: 1256425 (The Pile)

Max Activating Token Index: 494

Text #17

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.3812. Min Act: -0.0000

Data Index: 752430 (The Pile)

Max Activating Token Index: 867

Text #18

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.4117. Min Act: -0.0000

Data Index: 1463145 (The Pile)

Max Activating Token Index: 699

Text #19

Max Range: 0.5259. Min Range: -0.5259

Max Act: 0.3997. Min Act: -0.0000

Data Index: 291514 (The Pile)

Max Activating Token Index: 814