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

Dataset: The Pile

Neuron 536 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6713. Min Range: -1.6713

Max Act: 1.6713. Min Act: -0.0000

Data Index: 1749045 (The Pile)

Max Activating Token Index: 264

Text #1

Max Range: 1.6713. Min Range: -1.6713

Max Act: 1.6548. Min Act: -0.0000

Data Index: 148197 (The Pile)

Max Activating Token Index: 444

Text #2

Max Range: 1.6713. Min Range: -1.6713

Max Act: 1.4712. Min Act: -0.0000

Data Index: 1698133 (The Pile)

Max Activating Token Index: 228

Text #3

Max Range: 1.6713. Min Range: -1.6713

Max Act: 1.4452. Min Act: -0.0000

Data Index: 76107 (The Pile)

Max Activating Token Index: 179

Text #4

Max Range: 1.6713. Min Range: -1.6713

Max Act: 1.3828. Min Act: -0.0000

Data Index: 1343656 (The Pile)

Max Activating Token Index: 977

Text #5

Max Range: 1.6713. Min Range: -1.6713

Max Act: 1.4857. Min Act: -0.0000

Data Index: 1169569 (The Pile)

Max Activating Token Index: 708

Text #6

Max Range: 1.6713. Min Range: -1.6713

Max Act: 1.4092. Min Act: -0.0000

Data Index: 1548603 (The Pile)

Max Activating Token Index: 395

Text #7

Max Range: 1.6713. Min Range: -1.6713

Max Act: 1.4212. Min Act: -0.0000

Data Index: 1027809 (The Pile)

Max Activating Token Index: 280

Text #8

Max Range: 1.6713. Min Range: -1.6713

Max Act: 1.3646. Min Act: -0.0000

Data Index: 1130256 (The Pile)

Max Activating Token Index: 784

Text #9

Max Range: 1.6713. Min Range: -1.6713

Max Act: 1.4477. Min Act: -0.0000

Data Index: 1356229 (The Pile)

Max Activating Token Index: 798

Text #10

Max Range: 1.6713. Min Range: -1.6713

Max Act: 1.3192. Min Act: -0.0000

Data Index: 1565965 (The Pile)

Max Activating Token Index: 499

Text #11

Max Range: 1.6713. Min Range: -1.6713

Max Act: 1.3565. Min Act: -0.0000

Data Index: 1912195 (The Pile)

Max Activating Token Index: 254

Text #12

Max Range: 1.6713. Min Range: -1.6713

Max Act: 1.2207. Min Act: -0.0000

Data Index: 1119777 (The Pile)

Max Activating Token Index: 685

Text #13

Max Range: 1.6713. Min Range: -1.6713

Max Act: 1.3336. Min Act: -0.0000

Data Index: 109531 (The Pile)

Max Activating Token Index: 262

Text #14

Max Range: 1.6713. Min Range: -1.6713

Max Act: 1.3268. Min Act: -0.0000

Data Index: 1534529 (The Pile)

Max Activating Token Index: 647

Text #15

Max Range: 1.6713. Min Range: -1.6713

Max Act: 1.2818. Min Act: -0.0000

Data Index: 1451045 (The Pile)

Max Activating Token Index: 184

Text #16

Max Range: 1.6713. Min Range: -1.6713

Max Act: 1.3063. Min Act: -0.0000

Data Index: 1561266 (The Pile)

Max Activating Token Index: 393

Text #17

Max Range: 1.6713. Min Range: -1.6713

Max Act: 1.3029. Min Act: -0.0000

Data Index: 1184277 (The Pile)

Max Activating Token Index: 354

Text #18

Max Range: 1.6713. Min Range: -1.6713

Max Act: 1.3371. Min Act: -0.0000

Data Index: 1520848 (The Pile)

Max Activating Token Index: 273

Text #19

Max Range: 1.6713. Min Range: -1.6713

Max Act: 1.3216. Min Act: -0.0000

Data Index: 817456 (The Pile)

Max Activating Token Index: 915