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

Dataset: The Pile

Neuron 837 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.1959. Min Act: -0.0000

Data Index: 51171 (The Pile)

Max Activating Token Index: 139

Text #1

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.2974. Min Act: -0.0000

Data Index: 335205 (The Pile)

Max Activating Token Index: 77

Text #2

Max Range: 3.2974. Min Range: -3.2974

Max Act: 3.0447. Min Act: -0.0000

Data Index: 1863121 (The Pile)

Max Activating Token Index: 135

Text #3

Max Range: 3.2974. Min Range: -3.2974

Max Act: 2.7773. Min Act: -0.0000

Data Index: 767209 (The Pile)

Max Activating Token Index: 404

Text #4

Max Range: 3.2974. Min Range: -3.2974

Max Act: 2.7698. Min Act: -0.0000

Data Index: 1423387 (The Pile)

Max Activating Token Index: 129

Text #5

Max Range: 3.2974. Min Range: -3.2974

Max Act: 2.8791. Min Act: -0.0000

Data Index: 1305981 (The Pile)

Max Activating Token Index: 175

Text #6

Max Range: 3.2974. Min Range: -3.2974

Max Act: 2.9810. Min Act: -0.0000

Data Index: 612655 (The Pile)

Max Activating Token Index: 165

Text #7

Max Range: 3.2974. Min Range: -3.2974

Max Act: 2.8228. Min Act: -0.0000

Data Index: 448768 (The Pile)

Max Activating Token Index: 250

Text #8

Max Range: 3.2974. Min Range: -3.2974

Max Act: 2.7923. Min Act: -0.0000

Data Index: 1095679 (The Pile)

Max Activating Token Index: 145

Text #9

Max Range: 3.2974. Min Range: -3.2974

Max Act: 2.5244. Min Act: -0.0000

Data Index: 1922032 (The Pile)

Max Activating Token Index: 238

Text #10

Max Range: 3.2974. Min Range: -3.2974

Max Act: 2.6101. Min Act: -0.0000

Data Index: 1262613 (The Pile)

Max Activating Token Index: 770

Text #11

Max Range: 3.2974. Min Range: -3.2974

Max Act: 2.5559. Min Act: -0.0000

Data Index: 484019 (The Pile)

Max Activating Token Index: 153

Text #12

Max Range: 3.2974. Min Range: -3.2974

Max Act: 2.6760. Min Act: -0.0000

Data Index: 259595 (The Pile)

Max Activating Token Index: 298

Text #13

Max Range: 3.2974. Min Range: -3.2974

Max Act: 2.7899. Min Act: -0.0000

Data Index: 1891591 (The Pile)

Max Activating Token Index: 152

Text #14

Max Range: 3.2974. Min Range: -3.2974

Max Act: 2.6115. Min Act: -0.0000

Data Index: 1504234 (The Pile)

Max Activating Token Index: 297

Text #15

Max Range: 3.2974. Min Range: -3.2974

Max Act: 2.4917. Min Act: -0.0000

Data Index: 1019478 (The Pile)

Max Activating Token Index: 714

Text #16

Max Range: 3.2974. Min Range: -3.2974

Max Act: 2.7402. Min Act: -0.0000

Data Index: 1468356 (The Pile)

Max Activating Token Index: 506

Text #17

Max Range: 3.2974. Min Range: -3.2974

Max Act: 2.6025. Min Act: -0.0000

Data Index: 1641774 (The Pile)

Max Activating Token Index: 107

Text #18

Max Range: 3.2974. Min Range: -3.2974

Max Act: 2.6038. Min Act: -0.0000

Data Index: 1506250 (The Pile)

Max Activating Token Index: 630

Text #19

Max Range: 3.2974. Min Range: -3.2974

Max Act: 2.4346. Min Act: -0.0000

Data Index: 1705020 (The Pile)

Max Activating Token Index: 512