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

Dataset: The Pile

Neuron 2257 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.5392. Min Act: -0.0000

Data Index: 690278 (The Pile)

Max Activating Token Index: 1016

Text #1

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.5554. Min Act: -0.0000

Data Index: 1479780 (The Pile)

Max Activating Token Index: 159

Text #2

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.4323. Min Act: -0.0000

Data Index: 1324315 (The Pile)

Max Activating Token Index: 548

Text #3

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.4196. Min Act: -0.0000

Data Index: 391549 (The Pile)

Max Activating Token Index: 411

Text #4

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3448. Min Act: -0.0000

Data Index: 1437521 (The Pile)

Max Activating Token Index: 543

Text #5

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3826. Min Act: -0.0000

Data Index: 423538 (The Pile)

Max Activating Token Index: 543

Text #6

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3865. Min Act: -0.0000

Data Index: 1764611 (The Pile)

Max Activating Token Index: 904

Text #7

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3482. Min Act: -0.0000

Data Index: 515399 (The Pile)

Max Activating Token Index: 775

Text #8

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3846. Min Act: -0.0000

Data Index: 412294 (The Pile)

Max Activating Token Index: 101

Text #9

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3712. Min Act: -0.0000

Data Index: 153269 (The Pile)

Max Activating Token Index: 285

Text #10

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3327. Min Act: -0.0000

Data Index: 1655394 (The Pile)

Max Activating Token Index: 859

Text #11

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3373. Min Act: 0.0000

Data Index: 485824 (The Pile)

Max Activating Token Index: 146

Text #12

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3568. Min Act: -0.0000

Data Index: 1753493 (The Pile)

Max Activating Token Index: 1005

Text #13

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3429. Min Act: -0.0000

Data Index: 627404 (The Pile)

Max Activating Token Index: 623

Text #14

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3482. Min Act: -0.0000

Data Index: 519795 (The Pile)

Max Activating Token Index: 833

Text #15

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3399. Min Act: -0.0000

Data Index: 1684708 (The Pile)

Max Activating Token Index: 921

Text #16

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3019. Min Act: -0.0000

Data Index: 1322089 (The Pile)

Max Activating Token Index: 806

Text #17

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3271. Min Act: -0.0000

Data Index: 343862 (The Pile)

Max Activating Token Index: 228

Text #18

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3368. Min Act: -0.0000

Data Index: 770452 (The Pile)

Max Activating Token Index: 57

Text #19

Max Range: 0.5554. Min Range: -0.5554

Max Act: 0.3273. Min Act: 0.0000

Data Index: 988766 (The Pile)

Max Activating Token Index: 971