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

Dataset: The Pile

Neuron 4687 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.7234. Min Act: -0.0000

Data Index: 848938 (The Pile)

Max Activating Token Index: 757

Text #1

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.6168. Min Act: -0.0000

Data Index: 1790194 (The Pile)

Max Activating Token Index: 156

Text #2

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.6265. Min Act: -0.0000

Data Index: 240205 (The Pile)

Max Activating Token Index: 1005

Text #3

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5838. Min Act: -0.0000

Data Index: 1939596 (The Pile)

Max Activating Token Index: 40

Text #4

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.6229. Min Act: -0.0000

Data Index: 394455 (The Pile)

Max Activating Token Index: 584

Text #5

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5620. Min Act: -0.0000

Data Index: 25538 (The Pile)

Max Activating Token Index: 865

Text #6

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5907. Min Act: -0.0000

Data Index: 1868044 (The Pile)

Max Activating Token Index: 790

Text #7

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5985. Min Act: -0.0000

Data Index: 979067 (The Pile)

Max Activating Token Index: 969

Text #8

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.6807. Min Act: -0.0000

Data Index: 1672230 (The Pile)

Max Activating Token Index: 876

Text #9

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5795. Min Act: -0.0000

Data Index: 565220 (The Pile)

Max Activating Token Index: 86

Text #10

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5795. Min Act: -0.0000

Data Index: 862040 (The Pile)

Max Activating Token Index: 486

Text #11

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5189. Min Act: -0.0000

Data Index: 1097497 (The Pile)

Max Activating Token Index: 874

Text #12

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5607. Min Act: -0.0000

Data Index: 662033 (The Pile)

Max Activating Token Index: 1011

Text #13

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5407. Min Act: -0.0000

Data Index: 220558 (The Pile)

Max Activating Token Index: 86

Text #14

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5607. Min Act: -0.0000

Data Index: 559774 (The Pile)

Max Activating Token Index: 322

Text #15

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5817. Min Act: -0.0000

Data Index: 1222974 (The Pile)

Max Activating Token Index: 880

Text #16

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5436. Min Act: -0.0000

Data Index: 470422 (The Pile)

Max Activating Token Index: 254

Text #17

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5923. Min Act: -0.0000

Data Index: 388029 (The Pile)

Max Activating Token Index: 1021

Text #18

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.6016. Min Act: -0.0000

Data Index: 417658 (The Pile)

Max Activating Token Index: 736

Text #19

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5152. Min Act: -0.0000

Data Index: 706126 (The Pile)

Max Activating Token Index: 92