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

Dataset: The Pile

Neuron 4833 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: 1.0048. Min Range: -1.0048

Max Act: 0.7947. Min Act: -0.0000

Data Index: 532654 (The Pile)

Max Activating Token Index: 1003

Text #1

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.9490. Min Act: -0.0000

Data Index: 427770 (The Pile)

Max Activating Token Index: 368

Text #2

Max Range: 1.0048. Min Range: -1.0048

Max Act: 1.0048. Min Act: -0.0000

Data Index: 1954333 (The Pile)

Max Activating Token Index: 617

Text #3

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.9169. Min Act: -0.0000

Data Index: 1779158 (The Pile)

Max Activating Token Index: 723

Text #4

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.9417. Min Act: -0.0000

Data Index: 85722 (The Pile)

Max Activating Token Index: 314

Text #5

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.9065. Min Act: -0.0000

Data Index: 320769 (The Pile)

Max Activating Token Index: 456

Text #6

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.9068. Min Act: -0.0000

Data Index: 976737 (The Pile)

Max Activating Token Index: 543

Text #7

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.7731. Min Act: -0.0000

Data Index: 392386 (The Pile)

Max Activating Token Index: 226

Text #8

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.8055. Min Act: -0.0000

Data Index: 602258 (The Pile)

Max Activating Token Index: 933

Text #9

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.7465. Min Act: -0.0000

Data Index: 368160 (The Pile)

Max Activating Token Index: 672

Text #10

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.8044. Min Act: -0.0000

Data Index: 455021 (The Pile)

Max Activating Token Index: 310

Text #11

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.7228. Min Act: 0.0000

Data Index: 686091 (The Pile)

Max Activating Token Index: 254

Text #12

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.7095. Min Act: 0.0001

Data Index: 359556 (The Pile)

Max Activating Token Index: 15

Text #13

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.7100. Min Act: -0.0000

Data Index: 734604 (The Pile)

Max Activating Token Index: 421

Text #14

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.8741. Min Act: -0.0000

Data Index: 1516216 (The Pile)

Max Activating Token Index: 705

Text #15

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.6896. Min Act: 0.0000

Data Index: 1664939 (The Pile)

Max Activating Token Index: 63

Text #16

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.6442. Min Act: -0.0000

Data Index: 1145296 (The Pile)

Max Activating Token Index: 244

Text #17

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.7014. Min Act: 0.0000

Data Index: 430780 (The Pile)

Max Activating Token Index: 490

Text #18

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.6621. Min Act: -0.0000

Data Index: 888718 (The Pile)

Max Activating Token Index: 433

Text #19

Max Range: 1.0048. Min Range: -1.0048

Max Act: 0.7936. Min Act: -0.0000

Data Index: 1591171 (The Pile)

Max Activating Token Index: 767