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

Dataset: The Pile

Neuron 4249 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9812. Min Range: -0.9812

Max Act: 0.9812. Min Act: -0.0000

Data Index: 127064 (The Pile)

Max Activating Token Index: 931

Text #1

Max Range: 0.9812. Min Range: -0.9812

Max Act: 0.8254. Min Act: -0.0000

Data Index: 1198546 (The Pile)

Max Activating Token Index: 651

Text #2

Max Range: 0.9812. Min Range: -0.9812

Max Act: 0.8179. Min Act: -0.0000

Data Index: 918939 (The Pile)

Max Activating Token Index: 322

Text #3

Max Range: 0.9812. Min Range: -0.9812

Max Act: 0.8352. Min Act: -0.0000

Data Index: 1019728 (The Pile)

Max Activating Token Index: 548

Text #4

Max Range: 0.9812. Min Range: -0.9812

Max Act: 0.7753. Min Act: -0.0000

Data Index: 863412 (The Pile)

Max Activating Token Index: 51

Text #5

Max Range: 0.9812. Min Range: -0.9812

Max Act: 0.7701. Min Act: -0.0000

Data Index: 1283809 (The Pile)

Max Activating Token Index: 984

Text #6

Max Range: 0.9812. Min Range: -0.9812

Max Act: 0.6927. Min Act: -0.0000

Data Index: 514377 (The Pile)

Max Activating Token Index: 318

Text #7

Max Range: 0.9812. Min Range: -0.9812

Max Act: 0.6814. Min Act: -0.0000

Data Index: 418935 (The Pile)

Max Activating Token Index: 354

Text #8

Max Range: 0.9812. Min Range: -0.9812

Max Act: 0.6454. Min Act: -0.0000

Data Index: 161799 (The Pile)

Max Activating Token Index: 596

Text #9

Max Range: 0.9812. Min Range: -0.9812

Max Act: 0.6718. Min Act: -0.0000

Data Index: 239197 (The Pile)

Max Activating Token Index: 127

Text #10

Max Range: 0.9812. Min Range: -0.9812

Max Act: 0.6531. Min Act: -0.0000

Data Index: 1062148 (The Pile)

Max Activating Token Index: 510

Text #11

Max Range: 0.9812. Min Range: -0.9812

Max Act: 0.6073. Min Act: -0.0000

Data Index: 101522 (The Pile)

Max Activating Token Index: 510

Text #12

Max Range: 0.9812. Min Range: -0.9812

Max Act: 0.6236. Min Act: -0.0000

Data Index: 1909015 (The Pile)

Max Activating Token Index: 646

Text #13

Max Range: 0.9812. Min Range: -0.9812

Max Act: 0.6177. Min Act: -0.0000

Data Index: 204778 (The Pile)

Max Activating Token Index: 729

Text #14

Max Range: 0.9812. Min Range: -0.9812

Max Act: 0.6365. Min Act: -0.0000

Data Index: 1306038 (The Pile)

Max Activating Token Index: 75

Text #15

Max Range: 0.9812. Min Range: -0.9812

Max Act: 0.5767. Min Act: -0.0000

Data Index: 693902 (The Pile)

Max Activating Token Index: 648

Text #16

Max Range: 0.9812. Min Range: -0.9812

Max Act: 0.5930. Min Act: -0.0000

Data Index: 1010877 (The Pile)

Max Activating Token Index: 172

Text #17

Max Range: 0.9812. Min Range: -0.9812

Max Act: 0.6093. Min Act: -0.0000

Data Index: 906889 (The Pile)

Max Activating Token Index: 401

Text #18

Max Range: 0.9812. Min Range: -0.9812

Max Act: 0.6069. Min Act: -0.0000

Data Index: 735875 (The Pile)

Max Activating Token Index: 950

Text #19

Max Range: 0.9812. Min Range: -0.9812

Max Act: 0.6402. Min Act: -0.0000

Data Index: 267049 (The Pile)

Max Activating Token Index: 369