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

Dataset: The Pile

Neuron 3042 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: 0.7297. Min Range: -0.7297

Max Act: 0.7297. Min Act: -0.0000

Data Index: 1687761 (The Pile)

Max Activating Token Index: 708

Text #1

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.6906. Min Act: -0.0000

Data Index: 1997865 (The Pile)

Max Activating Token Index: 702

Text #2

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.6571. Min Act: -0.0000

Data Index: 839625 (The Pile)

Max Activating Token Index: 125

Text #3

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.5500. Min Act: -0.0000

Data Index: 1527059 (The Pile)

Max Activating Token Index: 161

Text #4

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.5506. Min Act: -0.0000

Data Index: 725814 (The Pile)

Max Activating Token Index: 247

Text #5

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.5190. Min Act: -0.0000

Data Index: 1003615 (The Pile)

Max Activating Token Index: 784

Text #6

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.5009. Min Act: -0.0000

Data Index: 205295 (The Pile)

Max Activating Token Index: 462

Text #7

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.5853. Min Act: -0.0000

Data Index: 306864 (The Pile)

Max Activating Token Index: 988

Text #8

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.5092. Min Act: -0.0000

Data Index: 1361515 (The Pile)

Max Activating Token Index: 959

Text #9

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.5013. Min Act: -0.0000

Data Index: 835334 (The Pile)

Max Activating Token Index: 354

Text #10

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.4476. Min Act: -0.0000

Data Index: 1417663 (The Pile)

Max Activating Token Index: 118

Text #11

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.3755. Min Act: -0.0000

Data Index: 1270814 (The Pile)

Max Activating Token Index: 1002

Text #12

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.4640. Min Act: -0.0000

Data Index: 1798572 (The Pile)

Max Activating Token Index: 210

Text #13

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.4748. Min Act: -0.0000

Data Index: 1494542 (The Pile)

Max Activating Token Index: 223

Text #14

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.4756. Min Act: -0.0000

Data Index: 258597 (The Pile)

Max Activating Token Index: 920

Text #15

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.4840. Min Act: -0.0000

Data Index: 1845184 (The Pile)

Max Activating Token Index: 766

Text #16

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.4159. Min Act: -0.0000

Data Index: 1787584 (The Pile)

Max Activating Token Index: 902

Text #17

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.4328. Min Act: -0.0000

Data Index: 994144 (The Pile)

Max Activating Token Index: 522

Text #18

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.4244. Min Act: -0.0000

Data Index: 857947 (The Pile)

Max Activating Token Index: 611

Text #19

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.4223. Min Act: -0.0000

Data Index: 1057080 (The Pile)

Max Activating Token Index: 886