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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1428 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.3873. Min Act: -0.0000

Data Index: 1377739 (Python Code)

Max Activating Token Index: 261

Text #1

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.4566. Min Act: -0.0000

Data Index: 552436 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.4336. Min Act: 0.0000

Data Index: 1412316 (Python Code)

Max Activating Token Index: 96

Text #3

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.4542. Min Act: 0.0000

Data Index: 1652152 (Python Code)

Max Activating Token Index: 22

Text #4

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.4358. Min Act: -0.0000

Data Index: 159366 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.4157. Min Act: 0.0000

Data Index: 1614067 (Python Code)

Max Activating Token Index: 1019

Text #6

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.4030. Min Act: -0.0000

Data Index: 1325061 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.4498. Min Act: -0.0000

Data Index: 1493841 (Python Code)

Max Activating Token Index: 262

Text #8

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.3657. Min Act: -0.0000

Data Index: 1417400 (Python Code)

Max Activating Token Index: 312

Text #9

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.4105. Min Act: -0.0000

Data Index: 579458 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.4191. Min Act: -0.0000

Data Index: 987657 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.4127. Min Act: -0.0000

Data Index: 1449774 (Python Code)

Max Activating Token Index: 36

Text #12

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.3869. Min Act: -0.0000

Data Index: 413247 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.3848. Min Act: 0.0000

Data Index: 1490488 (Python Code)

Max Activating Token Index: 82

Text #14

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.3764. Min Act: -0.0000

Data Index: 1124117 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.4088. Min Act: 0.0000

Data Index: 1543932 (Python Code)

Max Activating Token Index: 33

Text #16

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.2775. Min Act: -0.0000

Data Index: 1416742 (Python Code)

Max Activating Token Index: 294

Text #17

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.3843. Min Act: 0.0000

Data Index: 1444926 (Python Code)

Max Activating Token Index: 34

Text #18

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.3830. Min Act: -0.0000

Data Index: 1373555 (Python Code)

Max Activating Token Index: 782

Text #19

Max Range: 0.4566. Min Range: -0.4566

Max Act: 0.3553. Min Act: -0.0000

Data Index: 956537 (C4 (Web Text))

Max Activating Token Index: 853