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

Dataset: The Pile

Neuron 3672 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: 1.4223. Min Range: -1.4223

Max Act: 1.4223. Min Act: -0.0000

Data Index: 1654955 (The Pile)

Max Activating Token Index: 495

Text #1

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.3051. Min Act: -0.0000

Data Index: 924564 (The Pile)

Max Activating Token Index: 130

Text #2

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.3083. Min Act: -0.0000

Data Index: 906929 (The Pile)

Max Activating Token Index: 594

Text #3

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.3009. Min Act: -0.0000

Data Index: 154609 (The Pile)

Max Activating Token Index: 544

Text #4

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.2685. Min Act: -0.0000

Data Index: 1598284 (The Pile)

Max Activating Token Index: 637

Text #5

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.1131. Min Act: -0.0000

Data Index: 811342 (The Pile)

Max Activating Token Index: 910

Text #6

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.1834. Min Act: -0.0000

Data Index: 164074 (The Pile)

Max Activating Token Index: 760

Text #7

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.1989. Min Act: -0.0000

Data Index: 577647 (The Pile)

Max Activating Token Index: 1016

Text #8

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.1445. Min Act: -0.0000

Data Index: 469187 (The Pile)

Max Activating Token Index: 569

Text #9

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.2043. Min Act: -0.0000

Data Index: 592629 (The Pile)

Max Activating Token Index: 316

Text #10

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.0199. Min Act: -0.0000

Data Index: 1194936 (The Pile)

Max Activating Token Index: 613

Text #11

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.1377. Min Act: -0.0000

Data Index: 174439 (The Pile)

Max Activating Token Index: 345

Text #12

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.0632. Min Act: -0.0000

Data Index: 1798298 (The Pile)

Max Activating Token Index: 422

Text #13

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.0357. Min Act: -0.0000

Data Index: 677315 (The Pile)

Max Activating Token Index: 607

Text #14

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.1269. Min Act: -0.0000

Data Index: 142655 (The Pile)

Max Activating Token Index: 606

Text #15

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.1064. Min Act: -0.0000

Data Index: 809892 (The Pile)

Max Activating Token Index: 556

Text #16

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.1147. Min Act: -0.0000

Data Index: 1206112 (The Pile)

Max Activating Token Index: 432

Text #17

Max Range: 1.4223. Min Range: -1.4223

Max Act: 0.9606. Min Act: -0.0000

Data Index: 1307063 (The Pile)

Max Activating Token Index: 693

Text #18

Max Range: 1.4223. Min Range: -1.4223

Max Act: 1.0568. Min Act: -0.0000

Data Index: 1842976 (The Pile)

Max Activating Token Index: 109

Text #19

Max Range: 1.4223. Min Range: -1.4223

Max Act: 0.9399. Min Act: -0.0000

Data Index: 1320625 (The Pile)

Max Activating Token Index: 547