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

Dataset: The Pile

Neuron 2213 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.9147. Min Act: -0.0000

Data Index: 605535 (The Pile)

Max Activating Token Index: 590

Text #1

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.8664. Min Act: -0.0000

Data Index: 344259 (The Pile)

Max Activating Token Index: 442

Text #2

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.7674. Min Act: -0.0000

Data Index: 1396943 (The Pile)

Max Activating Token Index: 418

Text #3

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.7556. Min Act: -0.0000

Data Index: 276335 (The Pile)

Max Activating Token Index: 79

Text #4

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.7555. Min Act: -0.0000

Data Index: 314855 (The Pile)

Max Activating Token Index: 129

Text #5

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.8032. Min Act: -0.0000

Data Index: 388636 (The Pile)

Max Activating Token Index: 275

Text #6

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.6838. Min Act: -0.0000

Data Index: 198517 (The Pile)

Max Activating Token Index: 496

Text #7

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.6926. Min Act: -0.0000

Data Index: 727229 (The Pile)

Max Activating Token Index: 221

Text #8

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.7431. Min Act: -0.0000

Data Index: 1095312 (The Pile)

Max Activating Token Index: 122

Text #9

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.7321. Min Act: -0.0000

Data Index: 1703397 (The Pile)

Max Activating Token Index: 802

Text #10

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.7453. Min Act: -0.0000

Data Index: 1777939 (The Pile)

Max Activating Token Index: 114

Text #11

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.6460. Min Act: -0.0000

Data Index: 528687 (The Pile)

Max Activating Token Index: 438

Text #12

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.6934. Min Act: -0.0000

Data Index: 538162 (The Pile)

Max Activating Token Index: 508

Text #13

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.6810. Min Act: -0.0000

Data Index: 656450 (The Pile)

Max Activating Token Index: 851

Text #14

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.7013. Min Act: -0.0000

Data Index: 1918111 (The Pile)

Max Activating Token Index: 312

Text #15

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.6928. Min Act: -0.0000

Data Index: 1054345 (The Pile)

Max Activating Token Index: 743

Text #16

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.6760. Min Act: -0.0000

Data Index: 1231052 (The Pile)

Max Activating Token Index: 227

Text #17

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.7030. Min Act: -0.0000

Data Index: 357829 (The Pile)

Max Activating Token Index: 254

Text #18

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.6610. Min Act: -0.0000

Data Index: 943851 (The Pile)

Max Activating Token Index: 715

Text #19

Max Range: 0.9147. Min Range: -0.9147

Max Act: 0.6694. Min Act: -0.0000

Data Index: 721223 (The Pile)

Max Activating Token Index: 87