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

Dataset: The Pile

Neuron 3303 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 4.9000. Min Range: -4.9000

Max Act: 4.7754. Min Act: -0.0000

Data Index: 144949 (The Pile)

Max Activating Token Index: 701

Text #1

Max Range: 4.9000. Min Range: -4.9000

Max Act: 4.9000. Min Act: -0.0000

Data Index: 867281 (The Pile)

Max Activating Token Index: 714

Text #2

Max Range: 4.9000. Min Range: -4.9000

Max Act: 4.4215. Min Act: -0.0000

Data Index: 1640472 (The Pile)

Max Activating Token Index: 119

Text #3

Max Range: 4.9000. Min Range: -4.9000

Max Act: 4.3214. Min Act: -0.0000

Data Index: 1409480 (The Pile)

Max Activating Token Index: 89

Text #4

Max Range: 4.9000. Min Range: -4.9000

Max Act: 4.4720. Min Act: -0.0000

Data Index: 35952 (The Pile)

Max Activating Token Index: 919

Text #5

Max Range: 4.9000. Min Range: -4.9000

Max Act: 3.9758. Min Act: -0.0000

Data Index: 106457 (The Pile)

Max Activating Token Index: 716

Text #6

Max Range: 4.9000. Min Range: -4.9000

Max Act: 4.1543. Min Act: -0.0000

Data Index: 1938767 (The Pile)

Max Activating Token Index: 734

Text #7

Max Range: 4.9000. Min Range: -4.9000

Max Act: 4.1141. Min Act: -0.0000

Data Index: 652848 (The Pile)

Max Activating Token Index: 840

Text #8

Max Range: 4.9000. Min Range: -4.9000

Max Act: 4.2450. Min Act: -0.0000

Data Index: 497647 (The Pile)

Max Activating Token Index: 638

Text #9

Max Range: 4.9000. Min Range: -4.9000

Max Act: 4.2311. Min Act: -0.0000

Data Index: 667423 (The Pile)

Max Activating Token Index: 560

Text #10

Max Range: 4.9000. Min Range: -4.9000

Max Act: 4.0088. Min Act: -0.0000

Data Index: 1998138 (The Pile)

Max Activating Token Index: 267

Text #11

Max Range: 4.9000. Min Range: -4.9000

Max Act: 4.1673. Min Act: -0.0000

Data Index: 1615571 (The Pile)

Max Activating Token Index: 663

Text #12

Max Range: 4.9000. Min Range: -4.9000

Max Act: 4.4478. Min Act: -0.0000

Data Index: 1387887 (The Pile)

Max Activating Token Index: 486

Text #13

Max Range: 4.9000. Min Range: -4.9000

Max Act: 4.0965. Min Act: -0.0000

Data Index: 514634 (The Pile)

Max Activating Token Index: 1015

Text #14

Max Range: 4.9000. Min Range: -4.9000

Max Act: 4.2587. Min Act: -0.0000

Data Index: 1155836 (The Pile)

Max Activating Token Index: 977

Text #15

Max Range: 4.9000. Min Range: -4.9000

Max Act: 3.9517. Min Act: -0.0000

Data Index: 1150325 (The Pile)

Max Activating Token Index: 313

Text #16

Max Range: 4.9000. Min Range: -4.9000

Max Act: 3.9396. Min Act: -0.0000

Data Index: 656389 (The Pile)

Max Activating Token Index: 538

Text #17

Max Range: 4.9000. Min Range: -4.9000

Max Act: 3.9335. Min Act: -0.0000

Data Index: 1659027 (The Pile)

Max Activating Token Index: 479

Text #18

Max Range: 4.9000. Min Range: -4.9000

Max Act: 4.0838. Min Act: -0.0000

Data Index: 818796 (The Pile)

Max Activating Token Index: 861

Text #19

Max Range: 4.9000. Min Range: -4.9000

Max Act: 4.0762. Min Act: -0.0000

Data Index: 387522 (The Pile)

Max Activating Token Index: 309