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

Dataset: The Pile

Neuron 2025 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.9183. Min Act: -0.0000

Data Index: 1813522 (The Pile)

Max Activating Token Index: 713

Text #1

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.9573. Min Act: -0.0000

Data Index: 1261552 (The Pile)

Max Activating Token Index: 527

Text #2

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.9640. Min Act: -0.0000

Data Index: 1015049 (The Pile)

Max Activating Token Index: 493

Text #3

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.9492. Min Act: -0.0000

Data Index: 1680719 (The Pile)

Max Activating Token Index: 499

Text #4

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.7400. Min Act: -0.0000

Data Index: 1561633 (The Pile)

Max Activating Token Index: 775

Text #5

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.8649. Min Act: -0.0000

Data Index: 479146 (The Pile)

Max Activating Token Index: 91

Text #6

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.8443. Min Act: -0.0000

Data Index: 1948814 (The Pile)

Max Activating Token Index: 93

Text #7

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.7530. Min Act: -0.0000

Data Index: 1280020 (The Pile)

Max Activating Token Index: 382

Text #8

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.7755. Min Act: 0.0001

Data Index: 910711 (The Pile)

Max Activating Token Index: 501

Text #9

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.7462. Min Act: -0.0000

Data Index: 259126 (The Pile)

Max Activating Token Index: 694

Text #10

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.7249. Min Act: -0.0000

Data Index: 500340 (The Pile)

Max Activating Token Index: 735

Text #11

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.7489. Min Act: -0.0000

Data Index: 250016 (The Pile)

Max Activating Token Index: 450

Text #12

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.6680. Min Act: -0.0000

Data Index: 1832966 (The Pile)

Max Activating Token Index: 807

Text #13

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.6270. Min Act: -0.0000

Data Index: 1840277 (The Pile)

Max Activating Token Index: 940

Text #14

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.6775. Min Act: -0.0000

Data Index: 858021 (The Pile)

Max Activating Token Index: 499

Text #15

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.6405. Min Act: -0.0000

Data Index: 599798 (The Pile)

Max Activating Token Index: 850

Text #16

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.7355. Min Act: -0.0000

Data Index: 208374 (The Pile)

Max Activating Token Index: 684

Text #17

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.6606. Min Act: -0.0000

Data Index: 1246515 (The Pile)

Max Activating Token Index: 781

Text #18

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.6675. Min Act: -0.0000

Data Index: 209874 (The Pile)

Max Activating Token Index: 119

Text #19

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.7300. Min Act: -0.0000

Data Index: 1938121 (The Pile)

Max Activating Token Index: 368