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

Dataset: The Pile

Neuron 2274 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: 0.8466. Min Range: -0.8466

Max Act: 0.8466. Min Act: -0.0000

Data Index: 1463950 (The Pile)

Max Activating Token Index: 273

Text #1

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6782. Min Act: -0.0000

Data Index: 886007 (The Pile)

Max Activating Token Index: 309

Text #2

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6847. Min Act: -0.0000

Data Index: 414413 (The Pile)

Max Activating Token Index: 1016

Text #3

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6575. Min Act: -0.0000

Data Index: 1356824 (The Pile)

Max Activating Token Index: 15

Text #4

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6570. Min Act: -0.0000

Data Index: 881353 (The Pile)

Max Activating Token Index: 239

Text #5

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6499. Min Act: -0.0000

Data Index: 1382500 (The Pile)

Max Activating Token Index: 272

Text #6

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6634. Min Act: -0.0000

Data Index: 1125610 (The Pile)

Max Activating Token Index: 874

Text #7

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.5973. Min Act: -0.0000

Data Index: 911638 (The Pile)

Max Activating Token Index: 859

Text #8

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6262. Min Act: -0.0000

Data Index: 773319 (The Pile)

Max Activating Token Index: 192

Text #9

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6200. Min Act: 0.0000

Data Index: 1368670 (The Pile)

Max Activating Token Index: 256

Text #10

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6201. Min Act: -0.0000

Data Index: 1059535 (The Pile)

Max Activating Token Index: 248

Text #11

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6005. Min Act: 0.0000

Data Index: 1470101 (The Pile)

Max Activating Token Index: 32

Text #12

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6221. Min Act: -0.0000

Data Index: 634217 (The Pile)

Max Activating Token Index: 339

Text #13

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.5947. Min Act: -0.0000

Data Index: 39048 (The Pile)

Max Activating Token Index: 108

Text #14

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6189. Min Act: -0.0000

Data Index: 516599 (The Pile)

Max Activating Token Index: 7

Text #15

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.5967. Min Act: -0.0000

Data Index: 1833463 (The Pile)

Max Activating Token Index: 548

Text #16

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.6284. Min Act: -0.0000

Data Index: 1609654 (The Pile)

Max Activating Token Index: 41

Text #17

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.5886. Min Act: -0.0000

Data Index: 1796973 (The Pile)

Max Activating Token Index: 207

Text #18

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.5936. Min Act: -0.0000

Data Index: 1310881 (The Pile)

Max Activating Token Index: 311

Text #19

Max Range: 0.8466. Min Range: -0.8466

Max Act: 0.5913. Min Act: -0.0000

Data Index: 1313034 (The Pile)

Max Activating Token Index: 11