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

Dataset: The Pile

Neuron 4504 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: 1.9574. Min Range: -1.9574

Max Act: 1.8419. Min Act: -0.0000

Data Index: 677829 (The Pile)

Max Activating Token Index: 607

Text #1

Max Range: 1.9574. Min Range: -1.9574

Max Act: 1.9574. Min Act: -0.0000

Data Index: 285018 (The Pile)

Max Activating Token Index: 283

Text #2

Max Range: 1.9574. Min Range: -1.9574

Max Act: 1.8549. Min Act: -0.0000

Data Index: 1889126 (The Pile)

Max Activating Token Index: 798

Text #3

Max Range: 1.9574. Min Range: -1.9574

Max Act: 1.6887. Min Act: -0.0000

Data Index: 1866274 (The Pile)

Max Activating Token Index: 106

Text #4

Max Range: 1.9574. Min Range: -1.9574

Max Act: 1.6271. Min Act: -0.0000

Data Index: 531080 (The Pile)

Max Activating Token Index: 13

Text #5

Max Range: 1.9574. Min Range: -1.9574

Max Act: 1.4005. Min Act: -0.0000

Data Index: 1616875 (The Pile)

Max Activating Token Index: 1003

Text #6

Max Range: 1.9574. Min Range: -1.9574

Max Act: 1.4856. Min Act: -0.0000

Data Index: 472682 (The Pile)

Max Activating Token Index: 748

Text #7

Max Range: 1.9574. Min Range: -1.9574

Max Act: 1.4456. Min Act: -0.0000

Data Index: 1494853 (The Pile)

Max Activating Token Index: 524

Text #8

Max Range: 1.9574. Min Range: -1.9574

Max Act: 1.3448. Min Act: -0.0000

Data Index: 1539266 (The Pile)

Max Activating Token Index: 856

Text #9

Max Range: 1.9574. Min Range: -1.9574

Max Act: 1.4217. Min Act: -0.0000

Data Index: 1017558 (The Pile)

Max Activating Token Index: 302

Text #10

Max Range: 1.9574. Min Range: -1.9574

Max Act: 1.3111. Min Act: -0.0000

Data Index: 1739305 (The Pile)

Max Activating Token Index: 173

Text #11

Max Range: 1.9574. Min Range: -1.9574

Max Act: 1.3819. Min Act: -0.0000

Data Index: 1906 (The Pile)

Max Activating Token Index: 542

Text #12

Max Range: 1.9574. Min Range: -1.9574

Max Act: 1.2365. Min Act: -0.0000

Data Index: 156145 (The Pile)

Max Activating Token Index: 416

Text #13

Max Range: 1.9574. Min Range: -1.9574

Max Act: 1.2345. Min Act: -0.0000

Data Index: 1144868 (The Pile)

Max Activating Token Index: 624

Text #14

Max Range: 1.9574. Min Range: -1.9574

Max Act: 1.2906. Min Act: -0.0000

Data Index: 1020124 (The Pile)

Max Activating Token Index: 960

Text #15

Max Range: 1.9574. Min Range: -1.9574

Max Act: 1.2044. Min Act: -0.0000

Data Index: 773629 (The Pile)

Max Activating Token Index: 986

Text #16

Max Range: 1.9574. Min Range: -1.9574

Max Act: 1.2742. Min Act: -0.0000

Data Index: 1627248 (The Pile)

Max Activating Token Index: 270

Text #17

Max Range: 1.9574. Min Range: -1.9574

Max Act: 1.1822. Min Act: -0.0000

Data Index: 500160 (The Pile)

Max Activating Token Index: 153

Text #18

Max Range: 1.9574. Min Range: -1.9574

Max Act: 1.2510. Min Act: -0.0000

Data Index: 1711955 (The Pile)

Max Activating Token Index: 983

Text #19

Max Range: 1.9574. Min Range: -1.9574

Max Act: 1.1755. Min Act: -0.0000

Data Index: 438585 (The Pile)

Max Activating Token Index: 967