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

Dataset: The Pile

Neuron 1026 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: 0.4349. Min Range: -0.4349

Max Act: 0.4349. Min Act: -0.0000

Data Index: 1641373 (The Pile)

Max Activating Token Index: 511

Text #1

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.4156. Min Act: -0.0000

Data Index: 487183 (The Pile)

Max Activating Token Index: 700

Text #2

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.4092. Min Act: -0.0000

Data Index: 318611 (The Pile)

Max Activating Token Index: 179

Text #3

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3329. Min Act: -0.0000

Data Index: 1674959 (The Pile)

Max Activating Token Index: 238

Text #4

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3691. Min Act: -0.0000

Data Index: 930239 (The Pile)

Max Activating Token Index: 220

Text #5

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3582. Min Act: -0.0000

Data Index: 1059302 (The Pile)

Max Activating Token Index: 443

Text #6

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3297. Min Act: -0.0000

Data Index: 1574001 (The Pile)

Max Activating Token Index: 113

Text #7

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3367. Min Act: -0.0000

Data Index: 84651 (The Pile)

Max Activating Token Index: 437

Text #8

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3189. Min Act: -0.0000

Data Index: 1568561 (The Pile)

Max Activating Token Index: 977

Text #9

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2910. Min Act: -0.0000

Data Index: 992721 (The Pile)

Max Activating Token Index: 66

Text #10

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3343. Min Act: -0.0000

Data Index: 1746907 (The Pile)

Max Activating Token Index: 721

Text #11

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3122. Min Act: -0.0000

Data Index: 1610157 (The Pile)

Max Activating Token Index: 960

Text #12

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2995. Min Act: -0.0000

Data Index: 1068957 (The Pile)

Max Activating Token Index: 505

Text #13

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2777. Min Act: -0.0000

Data Index: 1250599 (The Pile)

Max Activating Token Index: 130

Text #14

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3102. Min Act: -0.0000

Data Index: 1507239 (The Pile)

Max Activating Token Index: 935

Text #15

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2781. Min Act: -0.0000

Data Index: 1537218 (The Pile)

Max Activating Token Index: 86

Text #16

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2659. Min Act: -0.0000

Data Index: 346608 (The Pile)

Max Activating Token Index: 902

Text #17

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2840. Min Act: -0.0000

Data Index: 1612786 (The Pile)

Max Activating Token Index: 903

Text #18

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2753. Min Act: -0.0000

Data Index: 1925048 (The Pile)

Max Activating Token Index: 708

Text #19

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2670. Min Act: -0.0000

Data Index: 1228968 (The Pile)

Max Activating Token Index: 342