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

Dataset: The Pile

Neuron 4091 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: 0.1195. Min Range: -0.1195

Max Act: 0.1195. Min Act: -0.0000

Data Index: 1636252 (The Pile)

Max Activating Token Index: 387

Text #1

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0911. Min Act: -0.0000

Data Index: 687231 (The Pile)

Max Activating Token Index: 214

Text #2

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0951. Min Act: -0.0000

Data Index: 178631 (The Pile)

Max Activating Token Index: 143

Text #3

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0976. Min Act: -0.0000

Data Index: 951178 (The Pile)

Max Activating Token Index: 633

Text #4

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0959. Min Act: -0.0000

Data Index: 684347 (The Pile)

Max Activating Token Index: 213

Text #5

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0745. Min Act: -0.0000

Data Index: 1511931 (The Pile)

Max Activating Token Index: 615

Text #6

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0717. Min Act: -0.0000

Data Index: 1823908 (The Pile)

Max Activating Token Index: 701

Text #7

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0588. Min Act: -0.0000

Data Index: 568728 (The Pile)

Max Activating Token Index: 293

Text #8

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0650. Min Act: -0.0000

Data Index: 1803405 (The Pile)

Max Activating Token Index: 569

Text #9

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0624. Min Act: -0.0000

Data Index: 124610 (The Pile)

Max Activating Token Index: 380

Text #10

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0624. Min Act: -0.0000

Data Index: 1995112 (The Pile)

Max Activating Token Index: 341

Text #11

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0630. Min Act: -0.0000

Data Index: 759933 (The Pile)

Max Activating Token Index: 300

Text #12

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0649. Min Act: -0.0000

Data Index: 1161534 (The Pile)

Max Activating Token Index: 635

Text #13

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0598. Min Act: -0.0000

Data Index: 596474 (The Pile)

Max Activating Token Index: 263

Text #14

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0617. Min Act: -0.0000

Data Index: 1178430 (The Pile)

Max Activating Token Index: 722

Text #15

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0469. Min Act: -0.0000

Data Index: 818506 (The Pile)

Max Activating Token Index: 747

Text #16

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0473. Min Act: -0.0000

Data Index: 557540 (The Pile)

Max Activating Token Index: 599

Text #17

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0467. Min Act: -0.0000

Data Index: 880642 (The Pile)

Max Activating Token Index: 418

Text #18

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0504. Min Act: -0.0000

Data Index: 1910390 (The Pile)

Max Activating Token Index: 246

Text #19

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0488. Min Act: -0.0000

Data Index: 637319 (The Pile)

Max Activating Token Index: 389