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

Dataset: The Pile

Neuron 1406 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.7419. Min Act: -0.0000

Data Index: 1923453 (The Pile)

Max Activating Token Index: 156

Text #1

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.5765. Min Act: -0.0000

Data Index: 1548366 (The Pile)

Max Activating Token Index: 280

Text #2

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.5763. Min Act: -0.0000

Data Index: 239985 (The Pile)

Max Activating Token Index: 92

Text #3

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.4961. Min Act: -0.0000

Data Index: 1199615 (The Pile)

Max Activating Token Index: 1020

Text #4

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.5465. Min Act: -0.0000

Data Index: 1030567 (The Pile)

Max Activating Token Index: 960

Text #5

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.5363. Min Act: -0.0000

Data Index: 916639 (The Pile)

Max Activating Token Index: 680

Text #6

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.5224. Min Act: -0.0000

Data Index: 1077302 (The Pile)

Max Activating Token Index: 565

Text #7

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.4518. Min Act: -0.0000

Data Index: 1316464 (The Pile)

Max Activating Token Index: 832

Text #8

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.4770. Min Act: -0.0000

Data Index: 15198 (The Pile)

Max Activating Token Index: 976

Text #9

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.5134. Min Act: -0.0000

Data Index: 659731 (The Pile)

Max Activating Token Index: 319

Text #10

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.4797. Min Act: -0.0000

Data Index: 1011158 (The Pile)

Max Activating Token Index: 161

Text #11

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.5093. Min Act: -0.0000

Data Index: 1666158 (The Pile)

Max Activating Token Index: 62

Text #12

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.4757. Min Act: -0.0000

Data Index: 1489397 (The Pile)

Max Activating Token Index: 869

Text #13

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.4428. Min Act: -0.0000

Data Index: 1285900 (The Pile)

Max Activating Token Index: 327

Text #14

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.4597. Min Act: -0.0000

Data Index: 1599805 (The Pile)

Max Activating Token Index: 267

Text #15

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.4478. Min Act: -0.0000

Data Index: 1185162 (The Pile)

Max Activating Token Index: 490

Text #16

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.4286. Min Act: -0.0000

Data Index: 270044 (The Pile)

Max Activating Token Index: 890

Text #17

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.4266. Min Act: -0.0000

Data Index: 470442 (The Pile)

Max Activating Token Index: 516

Text #18

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.4466. Min Act: -0.0000

Data Index: 1471924 (The Pile)

Max Activating Token Index: 427

Text #19

Max Range: 0.7419. Min Range: -0.7419

Max Act: 0.4026. Min Act: -0.0000

Data Index: 432450 (The Pile)

Max Activating Token Index: 175