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

Dataset: The Pile

Neuron 4522 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.6994. Min Act: -0.0000

Data Index: 384911 (The Pile)

Max Activating Token Index: 547

Text #1

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5610. Min Act: -0.0000

Data Index: 574605 (The Pile)

Max Activating Token Index: 662

Text #2

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5295. Min Act: -0.0000

Data Index: 257867 (The Pile)

Max Activating Token Index: 934

Text #3

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5176. Min Act: -0.0000

Data Index: 21316 (The Pile)

Max Activating Token Index: 784

Text #4

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5452. Min Act: -0.0000

Data Index: 650266 (The Pile)

Max Activating Token Index: 404

Text #5

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.3691. Min Act: -0.0000

Data Index: 1957724 (The Pile)

Max Activating Token Index: 988

Text #6

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4993. Min Act: -0.0000

Data Index: 161931 (The Pile)

Max Activating Token Index: 886

Text #7

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5089. Min Act: -0.0000

Data Index: 344917 (The Pile)

Max Activating Token Index: 528

Text #8

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4413. Min Act: -0.0000

Data Index: 1333666 (The Pile)

Max Activating Token Index: 961

Text #9

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4821. Min Act: -0.0000

Data Index: 351043 (The Pile)

Max Activating Token Index: 172

Text #10

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4682. Min Act: -0.0000

Data Index: 717463 (The Pile)

Max Activating Token Index: 107

Text #11

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4224. Min Act: -0.0000

Data Index: 11833 (The Pile)

Max Activating Token Index: 260

Text #12

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5064. Min Act: -0.0000

Data Index: 627294 (The Pile)

Max Activating Token Index: 702

Text #13

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4386. Min Act: -0.0000

Data Index: 859317 (The Pile)

Max Activating Token Index: 96

Text #14

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4064. Min Act: -0.0000

Data Index: 1984770 (The Pile)

Max Activating Token Index: 152

Text #15

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4093. Min Act: -0.0000

Data Index: 1162375 (The Pile)

Max Activating Token Index: 739

Text #16

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4358. Min Act: -0.0000

Data Index: 1356351 (The Pile)

Max Activating Token Index: 875

Text #17

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4768. Min Act: -0.0000

Data Index: 1665020 (The Pile)

Max Activating Token Index: 763

Text #18

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4172. Min Act: -0.0000

Data Index: 1108248 (The Pile)

Max Activating Token Index: 471

Text #19

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4052. Min Act: -0.0000

Data Index: 1811429 (The Pile)

Max Activating Token Index: 821