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

Dataset: The Pile

Neuron 349 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2212. Min Range: -1.2212

Max Act: 1.1033. Min Act: -0.0000

Data Index: 1549472 (The Pile)

Max Activating Token Index: 101

Text #1

Max Range: 1.2212. Min Range: -1.2212

Max Act: 1.2212. Min Act: -0.0000

Data Index: 756400 (The Pile)

Max Activating Token Index: 410

Text #2

Max Range: 1.2212. Min Range: -1.2212

Max Act: 1.0584. Min Act: -0.0000

Data Index: 1375518 (The Pile)

Max Activating Token Index: 94

Text #3

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.9611. Min Act: -0.0000

Data Index: 1064451 (The Pile)

Max Activating Token Index: 765

Text #4

Max Range: 1.2212. Min Range: -1.2212

Max Act: 1.0122. Min Act: -0.0000

Data Index: 340150 (The Pile)

Max Activating Token Index: 448

Text #5

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.9367. Min Act: -0.0000

Data Index: 1984977 (The Pile)

Max Activating Token Index: 8

Text #6

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.9454. Min Act: -0.0000

Data Index: 1743117 (The Pile)

Max Activating Token Index: 378

Text #7

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.8941. Min Act: -0.0000

Data Index: 1263882 (The Pile)

Max Activating Token Index: 36

Text #8

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.8912. Min Act: -0.0000

Data Index: 285827 (The Pile)

Max Activating Token Index: 873

Text #9

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.8802. Min Act: -0.0000

Data Index: 665790 (The Pile)

Max Activating Token Index: 538

Text #10

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.8386. Min Act: -0.0000

Data Index: 973711 (The Pile)

Max Activating Token Index: 705

Text #11

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.8739. Min Act: -0.0000

Data Index: 1888364 (The Pile)

Max Activating Token Index: 27

Text #12

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.8492. Min Act: -0.0000

Data Index: 1731325 (The Pile)

Max Activating Token Index: 591

Text #13

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.8342. Min Act: -0.0000

Data Index: 839871 (The Pile)

Max Activating Token Index: 223

Text #14

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.8361. Min Act: -0.0000

Data Index: 1523181 (The Pile)

Max Activating Token Index: 112

Text #15

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.8261. Min Act: -0.0000

Data Index: 1802334 (The Pile)

Max Activating Token Index: 178

Text #16

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.8098. Min Act: -0.0000

Data Index: 22312 (The Pile)

Max Activating Token Index: 817

Text #17

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.8415. Min Act: -0.0000

Data Index: 183515 (The Pile)

Max Activating Token Index: 379

Text #18

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.8076. Min Act: -0.0000

Data Index: 601458 (The Pile)

Max Activating Token Index: 463

Text #19

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.8327. Min Act: -0.0000

Data Index: 1559325 (The Pile)

Max Activating Token Index: 862