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

Dataset: The Pile

Neuron 3584 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.6122. Min Act: -0.0000

Data Index: 140405 (The Pile)

Max Activating Token Index: 1022

Text #1

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.5984. Min Act: -0.0000

Data Index: 123440 (The Pile)

Max Activating Token Index: 484

Text #2

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.5270. Min Act: -0.0000

Data Index: 1618019 (The Pile)

Max Activating Token Index: 902

Text #3

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.5310. Min Act: -0.0000

Data Index: 1952141 (The Pile)

Max Activating Token Index: 362

Text #4

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.5261. Min Act: -0.0000

Data Index: 968346 (The Pile)

Max Activating Token Index: 375

Text #5

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.5236. Min Act: -0.0000

Data Index: 1950293 (The Pile)

Max Activating Token Index: 316

Text #6

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.5078. Min Act: -0.0000

Data Index: 445431 (The Pile)

Max Activating Token Index: 802

Text #7

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.4699. Min Act: -0.0000

Data Index: 1020770 (The Pile)

Max Activating Token Index: 213

Text #8

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.4784. Min Act: 0.0000

Data Index: 1094312 (The Pile)

Max Activating Token Index: 740

Text #9

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.4876. Min Act: -0.0000

Data Index: 1472970 (The Pile)

Max Activating Token Index: 906

Text #10

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.4802. Min Act: -0.0000

Data Index: 1130178 (The Pile)

Max Activating Token Index: 918

Text #11

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.4875. Min Act: -0.0000

Data Index: 1473049 (The Pile)

Max Activating Token Index: 577

Text #12

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.4570. Min Act: -0.0000

Data Index: 1506541 (The Pile)

Max Activating Token Index: 593

Text #13

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.4750. Min Act: -0.0000

Data Index: 1374560 (The Pile)

Max Activating Token Index: 661

Text #14

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.4554. Min Act: -0.0000

Data Index: 1450347 (The Pile)

Max Activating Token Index: 570

Text #15

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.4614. Min Act: -0.0000

Data Index: 1873367 (The Pile)

Max Activating Token Index: 41

Text #16

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.4713. Min Act: -0.0000

Data Index: 1082729 (The Pile)

Max Activating Token Index: 224

Text #17

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.4542. Min Act: -0.0000

Data Index: 1674626 (The Pile)

Max Activating Token Index: 157

Text #18

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.4627. Min Act: -0.0000

Data Index: 201248 (The Pile)

Max Activating Token Index: 223

Text #19

Max Range: 0.6122. Min Range: -0.6122

Max Act: 0.4676. Min Act: -0.0000

Data Index: 1758345 (The Pile)

Max Activating Token Index: 667