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

Dataset: The Pile

Neuron 2029 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: 0.8532. Min Range: -0.8532

Max Act: 0.8532. Min Act: -0.0000

Data Index: 1935026 (The Pile)

Max Activating Token Index: 359

Text #1

Max Range: 0.8532. Min Range: -0.8532

Max Act: 0.7466. Min Act: -0.0000

Data Index: 202110 (The Pile)

Max Activating Token Index: 1017

Text #2

Max Range: 0.8532. Min Range: -0.8532

Max Act: 0.7747. Min Act: -0.0000

Data Index: 1211584 (The Pile)

Max Activating Token Index: 362

Text #3

Max Range: 0.8532. Min Range: -0.8532

Max Act: 0.7196. Min Act: -0.0000

Data Index: 943361 (The Pile)

Max Activating Token Index: 269

Text #4

Max Range: 0.8532. Min Range: -0.8532

Max Act: 0.6650. Min Act: -0.0000

Data Index: 1553191 (The Pile)

Max Activating Token Index: 584

Text #5

Max Range: 0.8532. Min Range: -0.8532

Max Act: 0.7083. Min Act: -0.0000

Data Index: 1903433 (The Pile)

Max Activating Token Index: 534

Text #6

Max Range: 0.8532. Min Range: -0.8532

Max Act: 0.6696. Min Act: -0.0000

Data Index: 901919 (The Pile)

Max Activating Token Index: 285

Text #7

Max Range: 0.8532. Min Range: -0.8532

Max Act: 0.6581. Min Act: -0.0000

Data Index: 1955272 (The Pile)

Max Activating Token Index: 628

Text #8

Max Range: 0.8532. Min Range: -0.8532

Max Act: 0.6024. Min Act: -0.0000

Data Index: 812263 (The Pile)

Max Activating Token Index: 794

Text #9

Max Range: 0.8532. Min Range: -0.8532

Max Act: 0.6774. Min Act: -0.0000

Data Index: 234379 (The Pile)

Max Activating Token Index: 19

Text #10

Max Range: 0.8532. Min Range: -0.8532

Max Act: 0.6265. Min Act: -0.0000

Data Index: 143228 (The Pile)

Max Activating Token Index: 459

Text #11

Max Range: 0.8532. Min Range: -0.8532

Max Act: 0.6128. Min Act: -0.0000

Data Index: 325815 (The Pile)

Max Activating Token Index: 495

Text #12

Max Range: 0.8532. Min Range: -0.8532

Max Act: 0.5850. Min Act: -0.0000

Data Index: 1994905 (The Pile)

Max Activating Token Index: 443

Text #13

Max Range: 0.8532. Min Range: -0.8532

Max Act: 0.6451. Min Act: -0.0000

Data Index: 204323 (The Pile)

Max Activating Token Index: 996

Text #14

Max Range: 0.8532. Min Range: -0.8532

Max Act: 0.5661. Min Act: -0.0000

Data Index: 1054128 (The Pile)

Max Activating Token Index: 120

Text #15

Max Range: 0.8532. Min Range: -0.8532

Max Act: 0.5892. Min Act: -0.0000

Data Index: 1896984 (The Pile)

Max Activating Token Index: 48

Text #16

Max Range: 0.8532. Min Range: -0.8532

Max Act: 0.5490. Min Act: -0.0000

Data Index: 361451 (The Pile)

Max Activating Token Index: 461

Text #17

Max Range: 0.8532. Min Range: -0.8532

Max Act: 0.5730. Min Act: -0.0000

Data Index: 1757960 (The Pile)

Max Activating Token Index: 226

Text #18

Max Range: 0.8532. Min Range: -0.8532

Max Act: 0.5213. Min Act: -0.0000

Data Index: 306833 (The Pile)

Max Activating Token Index: 515

Text #19

Max Range: 0.8532. Min Range: -0.8532

Max Act: 0.5074. Min Act: -0.0000

Data Index: 1280929 (The Pile)

Max Activating Token Index: 483