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

Dataset: The Pile

Neuron 4685 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: 0.5371. Min Range: -0.5371

Max Act: 0.5174. Min Act: -0.0000

Data Index: 387987 (The Pile)

Max Activating Token Index: 274

Text #1

Max Range: 0.5371. Min Range: -0.5371

Max Act: 0.5371. Min Act: -0.0000

Data Index: 443448 (The Pile)

Max Activating Token Index: 234

Text #2

Max Range: 0.5371. Min Range: -0.5371

Max Act: 0.4816. Min Act: -0.0000

Data Index: 1565231 (The Pile)

Max Activating Token Index: 21

Text #3

Max Range: 0.5371. Min Range: -0.5371

Max Act: 0.4374. Min Act: -0.0000

Data Index: 180066 (The Pile)

Max Activating Token Index: 982

Text #4

Max Range: 0.5371. Min Range: -0.5371

Max Act: 0.4364. Min Act: -0.0000

Data Index: 680088 (The Pile)

Max Activating Token Index: 127

Text #5

Max Range: 0.5371. Min Range: -0.5371

Max Act: 0.3594. Min Act: -0.0000

Data Index: 616455 (The Pile)

Max Activating Token Index: 662

Text #6

Max Range: 0.5371. Min Range: -0.5371

Max Act: 0.4391. Min Act: -0.0000

Data Index: 28420 (The Pile)

Max Activating Token Index: 488

Text #7

Max Range: 0.5371. Min Range: -0.5371

Max Act: 0.4563. Min Act: -0.0000

Data Index: 408599 (The Pile)

Max Activating Token Index: 210

Text #8

Max Range: 0.5371. Min Range: -0.5371

Max Act: 0.4485. Min Act: -0.0000

Data Index: 358844 (The Pile)

Max Activating Token Index: 196

Text #9

Max Range: 0.5371. Min Range: -0.5371

Max Act: 0.4152. Min Act: -0.0000

Data Index: 1903839 (The Pile)

Max Activating Token Index: 474

Text #10

Max Range: 0.5371. Min Range: -0.5371

Max Act: 0.3966. Min Act: -0.0000

Data Index: 543166 (The Pile)

Max Activating Token Index: 144

Text #11

Max Range: 0.5371. Min Range: -0.5371

Max Act: 0.3755. Min Act: -0.0000

Data Index: 409584 (The Pile)

Max Activating Token Index: 915

Text #12

Max Range: 0.5371. Min Range: -0.5371

Max Act: 0.4098. Min Act: -0.0000

Data Index: 1898722 (The Pile)

Max Activating Token Index: 435

Text #13

Max Range: 0.5371. Min Range: -0.5371

Max Act: 0.3831. Min Act: -0.0000

Data Index: 1171114 (The Pile)

Max Activating Token Index: 801

Text #14

Max Range: 0.5371. Min Range: -0.5371

Max Act: 0.3741. Min Act: -0.0000

Data Index: 566975 (The Pile)

Max Activating Token Index: 720

Text #15

Max Range: 0.5371. Min Range: -0.5371

Max Act: 0.3777. Min Act: -0.0000

Data Index: 1593325 (The Pile)

Max Activating Token Index: 364

Text #16

Max Range: 0.5371. Min Range: -0.5371

Max Act: 0.3983. Min Act: -0.0000

Data Index: 35627 (The Pile)

Max Activating Token Index: 604

Text #17

Max Range: 0.5371. Min Range: -0.5371

Max Act: 0.3806. Min Act: -0.0000

Data Index: 498757 (The Pile)

Max Activating Token Index: 408

Text #18

Max Range: 0.5371. Min Range: -0.5371

Max Act: 0.4207. Min Act: -0.0000

Data Index: 1964888 (The Pile)

Max Activating Token Index: 667

Text #19

Max Range: 0.5371. Min Range: -0.5371

Max Act: 0.3744. Min Act: -0.0000

Data Index: 408393 (The Pile)

Max Activating Token Index: 888