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

Dataset: The Pile

Neuron 2379 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: 1.7487. Min Range: -1.7487

Max Act: 1.6960. Min Act: -0.0000

Data Index: 652659 (The Pile)

Max Activating Token Index: 562

Text #1

Max Range: 1.7487. Min Range: -1.7487

Max Act: 1.7487. Min Act: -0.0000

Data Index: 1538681 (The Pile)

Max Activating Token Index: 700

Text #2

Max Range: 1.7487. Min Range: -1.7487

Max Act: 1.6250. Min Act: -0.0000

Data Index: 807846 (The Pile)

Max Activating Token Index: 778

Text #3

Max Range: 1.7487. Min Range: -1.7487

Max Act: 1.6593. Min Act: -0.0000

Data Index: 935718 (The Pile)

Max Activating Token Index: 623

Text #4

Max Range: 1.7487. Min Range: -1.7487

Max Act: 1.6162. Min Act: -0.0000

Data Index: 1480292 (The Pile)

Max Activating Token Index: 242

Text #5

Max Range: 1.7487. Min Range: -1.7487

Max Act: 1.6221. Min Act: -0.0000

Data Index: 1317854 (The Pile)

Max Activating Token Index: 481

Text #6

Max Range: 1.7487. Min Range: -1.7487

Max Act: 1.5142. Min Act: -0.0000

Data Index: 250758 (The Pile)

Max Activating Token Index: 124

Text #7

Max Range: 1.7487. Min Range: -1.7487

Max Act: 1.6049. Min Act: -0.0000

Data Index: 281249 (The Pile)

Max Activating Token Index: 158

Text #8

Max Range: 1.7487. Min Range: -1.7487

Max Act: 1.5852. Min Act: -0.0000

Data Index: 111525 (The Pile)

Max Activating Token Index: 921

Text #9

Max Range: 1.7487. Min Range: -1.7487

Max Act: 1.5483. Min Act: -0.0000

Data Index: 1863305 (The Pile)

Max Activating Token Index: 822

Text #10

Max Range: 1.7487. Min Range: -1.7487

Max Act: 1.4554. Min Act: -0.0000

Data Index: 1178025 (The Pile)

Max Activating Token Index: 857

Text #11

Max Range: 1.7487. Min Range: -1.7487

Max Act: 1.6193. Min Act: -0.0000

Data Index: 1470854 (The Pile)

Max Activating Token Index: 945

Text #12

Max Range: 1.7487. Min Range: -1.7487

Max Act: 1.4568. Min Act: -0.0000

Data Index: 1835437 (The Pile)

Max Activating Token Index: 185

Text #13

Max Range: 1.7487. Min Range: -1.7487

Max Act: 1.4804. Min Act: -0.0000

Data Index: 421587 (The Pile)

Max Activating Token Index: 581

Text #14

Max Range: 1.7487. Min Range: -1.7487

Max Act: 1.5626. Min Act: -0.0000

Data Index: 1788018 (The Pile)

Max Activating Token Index: 387

Text #15

Max Range: 1.7487. Min Range: -1.7487

Max Act: 1.2529. Min Act: -0.0000

Data Index: 889775 (The Pile)

Max Activating Token Index: 831

Text #16

Max Range: 1.7487. Min Range: -1.7487

Max Act: 1.3693. Min Act: -0.0000

Data Index: 607812 (The Pile)

Max Activating Token Index: 239

Text #17

Max Range: 1.7487. Min Range: -1.7487

Max Act: 1.4519. Min Act: -0.0000

Data Index: 1743995 (The Pile)

Max Activating Token Index: 427

Text #18

Max Range: 1.7487. Min Range: -1.7487

Max Act: 1.4915. Min Act: -0.0000

Data Index: 484079 (The Pile)

Max Activating Token Index: 711

Text #19

Max Range: 1.7487. Min Range: -1.7487

Max Act: 1.5486. Min Act: -0.0000

Data Index: 1859131 (The Pile)

Max Activating Token Index: 1022