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

Dataset: The Pile

Neuron 2099 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2555. Min Range: -1.2555

Max Act: 1.2555. Min Act: -0.0000

Data Index: 673392 (The Pile)

Max Activating Token Index: 797

Text #1

Max Range: 1.2555. Min Range: -1.2555

Max Act: 1.1751. Min Act: -0.0000

Data Index: 719028 (The Pile)

Max Activating Token Index: 5

Text #2

Max Range: 1.2555. Min Range: -1.2555

Max Act: 1.1966. Min Act: -0.0000

Data Index: 960764 (The Pile)

Max Activating Token Index: 14

Text #3

Max Range: 1.2555. Min Range: -1.2555

Max Act: 1.1006. Min Act: -0.0000

Data Index: 1257248 (The Pile)

Max Activating Token Index: 626

Text #4

Max Range: 1.2555. Min Range: -1.2555

Max Act: 1.1270. Min Act: -0.0000

Data Index: 1386237 (The Pile)

Max Activating Token Index: 403

Text #5

Max Range: 1.2555. Min Range: -1.2555

Max Act: 1.1025. Min Act: -0.0000

Data Index: 192352 (The Pile)

Max Activating Token Index: 7

Text #6

Max Range: 1.2555. Min Range: -1.2555

Max Act: 1.0680. Min Act: -0.0000

Data Index: 1019929 (The Pile)

Max Activating Token Index: 62

Text #7

Max Range: 1.2555. Min Range: -1.2555

Max Act: 1.0091. Min Act: -0.0000

Data Index: 261887 (The Pile)

Max Activating Token Index: 264

Text #8

Max Range: 1.2555. Min Range: -1.2555

Max Act: 1.0630. Min Act: -0.0000

Data Index: 1943314 (The Pile)

Max Activating Token Index: 29

Text #9

Max Range: 1.2555. Min Range: -1.2555

Max Act: 1.0088. Min Act: -0.0000

Data Index: 373887 (The Pile)

Max Activating Token Index: 948

Text #10

Max Range: 1.2555. Min Range: -1.2555

Max Act: 1.1109. Min Act: -0.0000

Data Index: 382746 (The Pile)

Max Activating Token Index: 728

Text #11

Max Range: 1.2555. Min Range: -1.2555

Max Act: 1.0248. Min Act: -0.0000

Data Index: 933640 (The Pile)

Max Activating Token Index: 999

Text #12

Max Range: 1.2555. Min Range: -1.2555

Max Act: 0.8687. Min Act: -0.0000

Data Index: 1373097 (The Pile)

Max Activating Token Index: 590

Text #13

Max Range: 1.2555. Min Range: -1.2555

Max Act: 1.0066. Min Act: -0.0000

Data Index: 766336 (The Pile)

Max Activating Token Index: 229

Text #14

Max Range: 1.2555. Min Range: -1.2555

Max Act: 0.9985. Min Act: -0.0000

Data Index: 349523 (The Pile)

Max Activating Token Index: 111

Text #15

Max Range: 1.2555. Min Range: -1.2555

Max Act: 1.0268. Min Act: -0.0000

Data Index: 495556 (The Pile)

Max Activating Token Index: 229

Text #16

Max Range: 1.2555. Min Range: -1.2555

Max Act: 0.9628. Min Act: -0.0000

Data Index: 1125188 (The Pile)

Max Activating Token Index: 1001

Text #17

Max Range: 1.2555. Min Range: -1.2555

Max Act: 0.9919. Min Act: -0.0000

Data Index: 647208 (The Pile)

Max Activating Token Index: 422

Text #18

Max Range: 1.2555. Min Range: -1.2555

Max Act: 0.9231. Min Act: -0.0000

Data Index: 300289 (The Pile)

Max Activating Token Index: 265

Text #19

Max Range: 1.2555. Min Range: -1.2555

Max Act: 0.9458. Min Act: -0.0000

Data Index: 574440 (The Pile)

Max Activating Token Index: 5