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

Dataset: The Pile

Neuron 1082 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3310. Min Range: -1.3310

Max Act: 1.3310. Min Act: -0.0000

Data Index: 818726 (The Pile)

Max Activating Token Index: 522

Text #1

Max Range: 1.3310. Min Range: -1.3310

Max Act: 1.1490. Min Act: -0.0000

Data Index: 139830 (The Pile)

Max Activating Token Index: 61

Text #2

Max Range: 1.3310. Min Range: -1.3310

Max Act: 1.2084. Min Act: -0.0000

Data Index: 504086 (The Pile)

Max Activating Token Index: 944

Text #3

Max Range: 1.3310. Min Range: -1.3310

Max Act: 1.1061. Min Act: -0.0000

Data Index: 1544766 (The Pile)

Max Activating Token Index: 500

Text #4

Max Range: 1.3310. Min Range: -1.3310

Max Act: 1.0254. Min Act: -0.0000

Data Index: 1349328 (The Pile)

Max Activating Token Index: 677

Text #5

Max Range: 1.3310. Min Range: -1.3310

Max Act: 1.0625. Min Act: -0.0000

Data Index: 1889737 (The Pile)

Max Activating Token Index: 100

Text #6

Max Range: 1.3310. Min Range: -1.3310

Max Act: 0.9868. Min Act: -0.0000

Data Index: 798321 (The Pile)

Max Activating Token Index: 298

Text #7

Max Range: 1.3310. Min Range: -1.3310

Max Act: 0.9721. Min Act: -0.0000

Data Index: 272095 (The Pile)

Max Activating Token Index: 804

Text #8

Max Range: 1.3310. Min Range: -1.3310

Max Act: 1.0430. Min Act: -0.0000

Data Index: 335219 (The Pile)

Max Activating Token Index: 421

Text #9

Max Range: 1.3310. Min Range: -1.3310

Max Act: 1.0890. Min Act: -0.0000

Data Index: 65496 (The Pile)

Max Activating Token Index: 166

Text #10

Max Range: 1.3310. Min Range: -1.3310

Max Act: 1.0887. Min Act: -0.0000

Data Index: 341195 (The Pile)

Max Activating Token Index: 999

Text #11

Max Range: 1.3310. Min Range: -1.3310

Max Act: 0.9776. Min Act: -0.0000

Data Index: 814506 (The Pile)

Max Activating Token Index: 932

Text #12

Max Range: 1.3310. Min Range: -1.3310

Max Act: 1.0163. Min Act: -0.0000

Data Index: 1046913 (The Pile)

Max Activating Token Index: 735

Text #13

Max Range: 1.3310. Min Range: -1.3310

Max Act: 0.9926. Min Act: -0.0000

Data Index: 1781840 (The Pile)

Max Activating Token Index: 445

Text #14

Max Range: 1.3310. Min Range: -1.3310

Max Act: 0.9924. Min Act: -0.0000

Data Index: 1020723 (The Pile)

Max Activating Token Index: 733

Text #15

Max Range: 1.3310. Min Range: -1.3310

Max Act: 0.9249. Min Act: -0.0000

Data Index: 1183297 (The Pile)

Max Activating Token Index: 570

Text #16

Max Range: 1.3310. Min Range: -1.3310

Max Act: 0.9247. Min Act: -0.0000

Data Index: 1087371 (The Pile)

Max Activating Token Index: 704

Text #17

Max Range: 1.3310. Min Range: -1.3310

Max Act: 0.8329. Min Act: -0.0000

Data Index: 1296143 (The Pile)

Max Activating Token Index: 777

Text #18

Max Range: 1.3310. Min Range: -1.3310

Max Act: 0.8869. Min Act: -0.0000

Data Index: 264873 (The Pile)

Max Activating Token Index: 135

Text #19

Max Range: 1.3310. Min Range: -1.3310

Max Act: 0.9434. Min Act: -0.0000

Data Index: 841396 (The Pile)

Max Activating Token Index: 188