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

Dataset: The Pile

Neuron 1300 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.4587. Min Act: -0.0000

Data Index: 516733 (The Pile)

Max Activating Token Index: 16

Text #1

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.5255. Min Act: -0.0000

Data Index: 7150 (The Pile)

Max Activating Token Index: 870

Text #2

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.4876. Min Act: -0.0000

Data Index: 1781575 (The Pile)

Max Activating Token Index: 328

Text #3

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.4492. Min Act: -0.0000

Data Index: 1456749 (The Pile)

Max Activating Token Index: 731

Text #4

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.4723. Min Act: -0.0000

Data Index: 124212 (The Pile)

Max Activating Token Index: 449

Text #5

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.4613. Min Act: 0.0000

Data Index: 947460 (The Pile)

Max Activating Token Index: 432

Text #6

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.4818. Min Act: -0.0000

Data Index: 1200872 (The Pile)

Max Activating Token Index: 781

Text #7

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.4151. Min Act: -0.0000

Data Index: 932011 (The Pile)

Max Activating Token Index: 987

Text #8

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.4309. Min Act: -0.0000

Data Index: 1061135 (The Pile)

Max Activating Token Index: 444

Text #9

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.4040. Min Act: -0.0000

Data Index: 236001 (The Pile)

Max Activating Token Index: 265

Text #10

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.4130. Min Act: -0.0000

Data Index: 1298198 (The Pile)

Max Activating Token Index: 533

Text #11

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.4150. Min Act: -0.0000

Data Index: 1544690 (The Pile)

Max Activating Token Index: 354

Text #12

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.3876. Min Act: -0.0000

Data Index: 1837073 (The Pile)

Max Activating Token Index: 962

Text #13

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.4119. Min Act: -0.0000

Data Index: 1937589 (The Pile)

Max Activating Token Index: 810

Text #14

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.3827. Min Act: -0.0000

Data Index: 1868266 (The Pile)

Max Activating Token Index: 750

Text #15

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.3846. Min Act: -0.0000

Data Index: 428284 (The Pile)

Max Activating Token Index: 20

Text #16

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.3558. Min Act: -0.0000

Data Index: 1478686 (The Pile)

Max Activating Token Index: 630

Text #17

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.4209. Min Act: -0.0000

Data Index: 565006 (The Pile)

Max Activating Token Index: 72

Text #18

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.3750. Min Act: -0.0000

Data Index: 1185180 (The Pile)

Max Activating Token Index: 159

Text #19

Max Range: 0.5255. Min Range: -0.5255

Max Act: 0.3885. Min Act: -0.0000

Data Index: 148231 (The Pile)

Max Activating Token Index: 600