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

Dataset: The Pile

Neuron 3201 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4541. Min Range: -4.4541

Max Act: 4.1338. Min Act: -0.0000

Data Index: 412269 (The Pile)

Max Activating Token Index: 842

Text #1

Max Range: 4.4541. Min Range: -4.4541

Max Act: 4.2720. Min Act: -0.0000

Data Index: 698886 (The Pile)

Max Activating Token Index: 904

Text #2

Max Range: 4.4541. Min Range: -4.4541

Max Act: 4.4114. Min Act: -0.0000

Data Index: 818266 (The Pile)

Max Activating Token Index: 558

Text #3

Max Range: 4.4541. Min Range: -4.4541

Max Act: 3.8720. Min Act: -0.0000

Data Index: 1697215 (The Pile)

Max Activating Token Index: 810

Text #4

Max Range: 4.4541. Min Range: -4.4541

Max Act: 4.2445. Min Act: -0.0000

Data Index: 552916 (The Pile)

Max Activating Token Index: 363

Text #5

Max Range: 4.4541. Min Range: -4.4541

Max Act: 4.2500. Min Act: -0.0000

Data Index: 1517686 (The Pile)

Max Activating Token Index: 235

Text #6

Max Range: 4.4541. Min Range: -4.4541

Max Act: 4.0370. Min Act: -0.0000

Data Index: 773904 (The Pile)

Max Activating Token Index: 859

Text #7

Max Range: 4.4541. Min Range: -4.4541

Max Act: 4.0079. Min Act: -0.0000

Data Index: 1120739 (The Pile)

Max Activating Token Index: 267

Text #8

Max Range: 4.4541. Min Range: -4.4541

Max Act: 3.7832. Min Act: -0.0000

Data Index: 1692899 (The Pile)

Max Activating Token Index: 712

Text #9

Max Range: 4.4541. Min Range: -4.4541

Max Act: 3.1219. Min Act: -0.0000

Data Index: 1085133 (The Pile)

Max Activating Token Index: 1002

Text #10

Max Range: 4.4541. Min Range: -4.4541

Max Act: 3.7893. Min Act: -0.0000

Data Index: 669704 (The Pile)

Max Activating Token Index: 388

Text #11

Max Range: 4.4541. Min Range: -4.4541

Max Act: 3.4766. Min Act: -0.0000

Data Index: 932691 (The Pile)

Max Activating Token Index: 682

Text #12

Max Range: 4.4541. Min Range: -4.4541

Max Act: 4.4541. Min Act: -0.0000

Data Index: 1481577 (The Pile)

Max Activating Token Index: 838

Text #13

Max Range: 4.4541. Min Range: -4.4541

Max Act: 3.8514. Min Act: -0.0000

Data Index: 1910940 (The Pile)

Max Activating Token Index: 717

Text #14

Max Range: 4.4541. Min Range: -4.4541

Max Act: 3.7216. Min Act: -0.0000

Data Index: 867617 (The Pile)

Max Activating Token Index: 346

Text #15

Max Range: 4.4541. Min Range: -4.4541

Max Act: 3.8461. Min Act: -0.0000

Data Index: 1155928 (The Pile)

Max Activating Token Index: 64

Text #16

Max Range: 4.4541. Min Range: -4.4541

Max Act: 3.6801. Min Act: -0.0000

Data Index: 1378050 (The Pile)

Max Activating Token Index: 720

Text #17

Max Range: 4.4541. Min Range: -4.4541

Max Act: 3.1865. Min Act: -0.0000

Data Index: 84406 (The Pile)

Max Activating Token Index: 838

Text #18

Max Range: 4.4541. Min Range: -4.4541

Max Act: 3.9789. Min Act: -0.0000

Data Index: 355275 (The Pile)

Max Activating Token Index: 809

Text #19

Max Range: 4.4541. Min Range: -4.4541

Max Act: 3.4869. Min Act: -0.0000

Data Index: 1452387 (The Pile)

Max Activating Token Index: 770