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

Dataset: The Pile

Neuron 504 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.6085. Min Act: -0.0000

Data Index: 1270384 (The Pile)

Max Activating Token Index: 20

Text #1

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.5959. Min Act: -0.0000

Data Index: 1447753 (The Pile)

Max Activating Token Index: 668

Text #2

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.5538. Min Act: -0.0000

Data Index: 531318 (The Pile)

Max Activating Token Index: 448

Text #3

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.5291. Min Act: -0.0000

Data Index: 837432 (The Pile)

Max Activating Token Index: 518

Text #4

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.5904. Min Act: -0.0000

Data Index: 1105975 (The Pile)

Max Activating Token Index: 394

Text #5

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.5504. Min Act: -0.0000

Data Index: 1128925 (The Pile)

Max Activating Token Index: 982

Text #6

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.5249. Min Act: -0.0000

Data Index: 685644 (The Pile)

Max Activating Token Index: 605

Text #7

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.5410. Min Act: -0.0000

Data Index: 654705 (The Pile)

Max Activating Token Index: 306

Text #8

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.5181. Min Act: -0.0000

Data Index: 259508 (The Pile)

Max Activating Token Index: 331

Text #9

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.5202. Min Act: -0.0000

Data Index: 381143 (The Pile)

Max Activating Token Index: 472

Text #10

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.5015. Min Act: -0.0000

Data Index: 1312442 (The Pile)

Max Activating Token Index: 469

Text #11

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.5449. Min Act: -0.0000

Data Index: 1979473 (The Pile)

Max Activating Token Index: 498

Text #12

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.5326. Min Act: -0.0000

Data Index: 1594605 (The Pile)

Max Activating Token Index: 34

Text #13

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.5482. Min Act: -0.0000

Data Index: 986849 (The Pile)

Max Activating Token Index: 257

Text #14

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.5298. Min Act: -0.0000

Data Index: 447117 (The Pile)

Max Activating Token Index: 548

Text #15

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.5107. Min Act: -0.0000

Data Index: 1113699 (The Pile)

Max Activating Token Index: 536

Text #16

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.5074. Min Act: -0.0000

Data Index: 1598988 (The Pile)

Max Activating Token Index: 690

Text #17

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.4852. Min Act: -0.0000

Data Index: 432323 (The Pile)

Max Activating Token Index: 641

Text #18

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.4856. Min Act: -0.0000

Data Index: 1751852 (The Pile)

Max Activating Token Index: 385

Text #19

Max Range: 0.6085. Min Range: -0.6085

Max Act: 0.4992. Min Act: -0.0000

Data Index: 713479 (The Pile)

Max Activating Token Index: 907