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

Dataset: The Pile

Neuron 5010 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: 3.5954. Min Range: -3.5954

Max Act: 3.5954. Min Act: -0.0000

Data Index: 775265 (The Pile)

Max Activating Token Index: 100

Text #1

Max Range: 3.5954. Min Range: -3.5954

Max Act: 3.5760. Min Act: -0.0000

Data Index: 140106 (The Pile)

Max Activating Token Index: 24

Text #2

Max Range: 3.5954. Min Range: -3.5954

Max Act: 3.3465. Min Act: -0.0000

Data Index: 1655022 (The Pile)

Max Activating Token Index: 30

Text #3

Max Range: 3.5954. Min Range: -3.5954

Max Act: 3.3132. Min Act: -0.0000

Data Index: 999169 (The Pile)

Max Activating Token Index: 350

Text #4

Max Range: 3.5954. Min Range: -3.5954

Max Act: 3.3831. Min Act: -0.0000

Data Index: 3995 (The Pile)

Max Activating Token Index: 381

Text #5

Max Range: 3.5954. Min Range: -3.5954

Max Act: 3.1994. Min Act: -0.0000

Data Index: 1542718 (The Pile)

Max Activating Token Index: 485

Text #6

Max Range: 3.5954. Min Range: -3.5954

Max Act: 3.1989. Min Act: -0.0000

Data Index: 1235000 (The Pile)

Max Activating Token Index: 29

Text #7

Max Range: 3.5954. Min Range: -3.5954

Max Act: 3.1731. Min Act: -0.0000

Data Index: 992918 (The Pile)

Max Activating Token Index: 119

Text #8

Max Range: 3.5954. Min Range: -3.5954

Max Act: 2.9418. Min Act: -0.0000

Data Index: 1748669 (The Pile)

Max Activating Token Index: 214

Text #9

Max Range: 3.5954. Min Range: -3.5954

Max Act: 2.9212. Min Act: -0.0000

Data Index: 135676 (The Pile)

Max Activating Token Index: 238

Text #10

Max Range: 3.5954. Min Range: -3.5954

Max Act: 3.1878. Min Act: -0.0000

Data Index: 1243544 (The Pile)

Max Activating Token Index: 167

Text #11

Max Range: 3.5954. Min Range: -3.5954

Max Act: 2.7786. Min Act: -0.0000

Data Index: 1372077 (The Pile)

Max Activating Token Index: 681

Text #12

Max Range: 3.5954. Min Range: -3.5954

Max Act: 2.8615. Min Act: -0.0000

Data Index: 182103 (The Pile)

Max Activating Token Index: 433

Text #13

Max Range: 3.5954. Min Range: -3.5954

Max Act: 2.8502. Min Act: -0.0000

Data Index: 940027 (The Pile)

Max Activating Token Index: 727

Text #14

Max Range: 3.5954. Min Range: -3.5954

Max Act: 2.5985. Min Act: -0.0000

Data Index: 978551 (The Pile)

Max Activating Token Index: 880

Text #15

Max Range: 3.5954. Min Range: -3.5954

Max Act: 2.4578. Min Act: -0.0000

Data Index: 1119659 (The Pile)

Max Activating Token Index: 989

Text #16

Max Range: 3.5954. Min Range: -3.5954

Max Act: 2.9652. Min Act: -0.0000

Data Index: 1288041 (The Pile)

Max Activating Token Index: 373

Text #17

Max Range: 3.5954. Min Range: -3.5954

Max Act: 2.8181. Min Act: -0.0000

Data Index: 242903 (The Pile)

Max Activating Token Index: 259

Text #18

Max Range: 3.5954. Min Range: -3.5954

Max Act: 2.6851. Min Act: -0.0000

Data Index: 1257955 (The Pile)

Max Activating Token Index: 758

Text #19

Max Range: 3.5954. Min Range: -3.5954

Max Act: 2.8129. Min Act: -0.0000

Data Index: 1754264 (The Pile)

Max Activating Token Index: 561