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

Dataset: The Pile

Neuron 3607 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: 0.9354. Min Range: -0.9354

Max Act: 0.9354. Min Act: -0.0000

Data Index: 599769 (The Pile)

Max Activating Token Index: 414

Text #1

Max Range: 0.9354. Min Range: -0.9354

Max Act: 0.8231. Min Act: -0.0000

Data Index: 891764 (The Pile)

Max Activating Token Index: 376

Text #2

Max Range: 0.9354. Min Range: -0.9354

Max Act: 0.8695. Min Act: -0.0000

Data Index: 1898627 (The Pile)

Max Activating Token Index: 469

Text #3

Max Range: 0.9354. Min Range: -0.9354

Max Act: 0.8016. Min Act: -0.0000

Data Index: 916102 (The Pile)

Max Activating Token Index: 531

Text #4

Max Range: 0.9354. Min Range: -0.9354

Max Act: 0.7814. Min Act: -0.0000

Data Index: 403599 (The Pile)

Max Activating Token Index: 52

Text #5

Max Range: 0.9354. Min Range: -0.9354

Max Act: 0.7289. Min Act: -0.0000

Data Index: 1438832 (The Pile)

Max Activating Token Index: 607

Text #6

Max Range: 0.9354. Min Range: -0.9354

Max Act: 0.7096. Min Act: -0.0000

Data Index: 1213335 (The Pile)

Max Activating Token Index: 55

Text #7

Max Range: 0.9354. Min Range: -0.9354

Max Act: 0.6708. Min Act: -0.0000

Data Index: 742220 (The Pile)

Max Activating Token Index: 785

Text #8

Max Range: 0.9354. Min Range: -0.9354

Max Act: 0.6256. Min Act: -0.0000

Data Index: 329522 (The Pile)

Max Activating Token Index: 414

Text #9

Max Range: 0.9354. Min Range: -0.9354

Max Act: 0.6518. Min Act: -0.0000

Data Index: 903047 (The Pile)

Max Activating Token Index: 201

Text #10

Max Range: 0.9354. Min Range: -0.9354

Max Act: 0.6675. Min Act: -0.0000

Data Index: 1025830 (The Pile)

Max Activating Token Index: 668

Text #11

Max Range: 0.9354. Min Range: -0.9354

Max Act: 0.6032. Min Act: -0.0000

Data Index: 1105529 (The Pile)

Max Activating Token Index: 620

Text #12

Max Range: 0.9354. Min Range: -0.9354

Max Act: 0.6623. Min Act: -0.0000

Data Index: 1515634 (The Pile)

Max Activating Token Index: 130

Text #13

Max Range: 0.9354. Min Range: -0.9354

Max Act: 0.6270. Min Act: -0.0000

Data Index: 259809 (The Pile)

Max Activating Token Index: 859

Text #14

Max Range: 0.9354. Min Range: -0.9354

Max Act: 0.6239. Min Act: -0.0000

Data Index: 1379055 (The Pile)

Max Activating Token Index: 1014

Text #15

Max Range: 0.9354. Min Range: -0.9354

Max Act: 0.5984. Min Act: -0.0000

Data Index: 1200958 (The Pile)

Max Activating Token Index: 263

Text #16

Max Range: 0.9354. Min Range: -0.9354

Max Act: 0.5925. Min Act: -0.0000

Data Index: 217910 (The Pile)

Max Activating Token Index: 679

Text #17

Max Range: 0.9354. Min Range: -0.9354

Max Act: 0.5842. Min Act: -0.0000

Data Index: 903873 (The Pile)

Max Activating Token Index: 221

Text #18

Max Range: 0.9354. Min Range: -0.9354

Max Act: 0.5617. Min Act: -0.0000

Data Index: 397186 (The Pile)

Max Activating Token Index: 569

Text #19

Max Range: 0.9354. Min Range: -0.9354

Max Act: 0.5511. Min Act: -0.0000

Data Index: 1806884 (The Pile)

Max Activating Token Index: 926