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

Dataset: The Pile

Neuron 1553 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9147. Min Range: -3.9147

Max Act: 3.9147. Min Act: -0.0000

Data Index: 172877 (The Pile)

Max Activating Token Index: 312

Text #1

Max Range: 3.9147. Min Range: -3.9147

Max Act: 3.7482. Min Act: -0.0000

Data Index: 1683368 (The Pile)

Max Activating Token Index: 30

Text #2

Max Range: 3.9147. Min Range: -3.9147

Max Act: 3.6506. Min Act: -0.0000

Data Index: 272870 (The Pile)

Max Activating Token Index: 126

Text #3

Max Range: 3.9147. Min Range: -3.9147

Max Act: 3.6393. Min Act: -0.0000

Data Index: 1197420 (The Pile)

Max Activating Token Index: 184

Text #4

Max Range: 3.9147. Min Range: -3.9147

Max Act: 3.5659. Min Act: -0.0000

Data Index: 713911 (The Pile)

Max Activating Token Index: 20

Text #5

Max Range: 3.9147. Min Range: -3.9147

Max Act: 3.3796. Min Act: -0.0000

Data Index: 803530 (The Pile)

Max Activating Token Index: 114

Text #6

Max Range: 3.9147. Min Range: -3.9147

Max Act: 3.6460. Min Act: -0.0000

Data Index: 704395 (The Pile)

Max Activating Token Index: 221

Text #7

Max Range: 3.9147. Min Range: -3.9147

Max Act: 3.3277. Min Act: -0.0000

Data Index: 1924962 (The Pile)

Max Activating Token Index: 422

Text #8

Max Range: 3.9147. Min Range: -3.9147

Max Act: 3.4783. Min Act: -0.0000

Data Index: 795759 (The Pile)

Max Activating Token Index: 357

Text #9

Max Range: 3.9147. Min Range: -3.9147

Max Act: 3.3130. Min Act: -0.0000

Data Index: 1543880 (The Pile)

Max Activating Token Index: 104

Text #10

Max Range: 3.9147. Min Range: -3.9147

Max Act: 3.1403. Min Act: -0.0000

Data Index: 1217097 (The Pile)

Max Activating Token Index: 128

Text #11

Max Range: 3.9147. Min Range: -3.9147

Max Act: 3.1122. Min Act: -0.0000

Data Index: 21657 (The Pile)

Max Activating Token Index: 496

Text #12

Max Range: 3.9147. Min Range: -3.9147

Max Act: 3.2650. Min Act: -0.0000

Data Index: 1732676 (The Pile)

Max Activating Token Index: 174

Text #13

Max Range: 3.9147. Min Range: -3.9147

Max Act: 2.9641. Min Act: -0.0000

Data Index: 86776 (The Pile)

Max Activating Token Index: 827

Text #14

Max Range: 3.9147. Min Range: -3.9147

Max Act: 3.1057. Min Act: -0.0000

Data Index: 31170 (The Pile)

Max Activating Token Index: 27

Text #15

Max Range: 3.9147. Min Range: -3.9147

Max Act: 3.2238. Min Act: -0.0000

Data Index: 73977 (The Pile)

Max Activating Token Index: 75

Text #16

Max Range: 3.9147. Min Range: -3.9147

Max Act: 3.1869. Min Act: -0.0000

Data Index: 1043928 (The Pile)

Max Activating Token Index: 287

Text #17

Max Range: 3.9147. Min Range: -3.9147

Max Act: 3.3728. Min Act: -0.0000

Data Index: 1583960 (The Pile)

Max Activating Token Index: 121

Text #18

Max Range: 3.9147. Min Range: -3.9147

Max Act: 3.3801. Min Act: -0.0000

Data Index: 1158712 (The Pile)

Max Activating Token Index: 105

Text #19

Max Range: 3.9147. Min Range: -3.9147

Max Act: 3.1898. Min Act: -0.0000

Data Index: 247149 (The Pile)

Max Activating Token Index: 490