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

Dataset: The Pile

Neuron 1956 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.4705. Min Act: -0.0000

Data Index: 917485 (The Pile)

Max Activating Token Index: 530

Text #1

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.3625. Min Act: -0.0000

Data Index: 342116 (The Pile)

Max Activating Token Index: 484

Text #2

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.4075. Min Act: -0.0000

Data Index: 126510 (The Pile)

Max Activating Token Index: 405

Text #3

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.4002. Min Act: -0.0000

Data Index: 153451 (The Pile)

Max Activating Token Index: 771

Text #4

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.3609. Min Act: -0.0000

Data Index: 1674284 (The Pile)

Max Activating Token Index: 565

Text #5

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.3455. Min Act: -0.0000

Data Index: 1354311 (The Pile)

Max Activating Token Index: 340

Text #6

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.3377. Min Act: -0.0000

Data Index: 1693932 (The Pile)

Max Activating Token Index: 924

Text #7

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.3746. Min Act: -0.0000

Data Index: 156662 (The Pile)

Max Activating Token Index: 234

Text #8

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.3399. Min Act: -0.0000

Data Index: 1282812 (The Pile)

Max Activating Token Index: 505

Text #9

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.3618. Min Act: -0.0000

Data Index: 1685051 (The Pile)

Max Activating Token Index: 344

Text #10

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.3428. Min Act: -0.0000

Data Index: 701433 (The Pile)

Max Activating Token Index: 517

Text #11

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.3161. Min Act: -0.0000

Data Index: 690594 (The Pile)

Max Activating Token Index: 600

Text #12

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.2868. Min Act: -0.0000

Data Index: 536707 (The Pile)

Max Activating Token Index: 949

Text #13

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.3608. Min Act: -0.0000

Data Index: 1542315 (The Pile)

Max Activating Token Index: 951

Text #14

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.3127. Min Act: -0.0000

Data Index: 1315008 (The Pile)

Max Activating Token Index: 95

Text #15

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.3383. Min Act: -0.0000

Data Index: 1389646 (The Pile)

Max Activating Token Index: 534

Text #16

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.3127. Min Act: -0.0000

Data Index: 23793 (The Pile)

Max Activating Token Index: 613

Text #17

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.3119. Min Act: -0.0000

Data Index: 234860 (The Pile)

Max Activating Token Index: 575

Text #18

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.3254. Min Act: -0.0000

Data Index: 107088 (The Pile)

Max Activating Token Index: 871

Text #19

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.3268. Min Act: -0.0000

Data Index: 901621 (The Pile)

Max Activating Token Index: 820