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

Dataset: The Pile

Neuron 1580 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: 1.4929. Min Range: -1.4929

Max Act: 1.4929. Min Act: -0.0000

Data Index: 434450 (The Pile)

Max Activating Token Index: 819

Text #1

Max Range: 1.4929. Min Range: -1.4929

Max Act: 1.3900. Min Act: -0.0000

Data Index: 1673626 (The Pile)

Max Activating Token Index: 313

Text #2

Max Range: 1.4929. Min Range: -1.4929

Max Act: 1.3606. Min Act: -0.0000

Data Index: 1986749 (The Pile)

Max Activating Token Index: 468

Text #3

Max Range: 1.4929. Min Range: -1.4929

Max Act: 1.3501. Min Act: -0.0000

Data Index: 1473782 (The Pile)

Max Activating Token Index: 728

Text #4

Max Range: 1.4929. Min Range: -1.4929

Max Act: 1.4183. Min Act: -0.0000

Data Index: 954108 (The Pile)

Max Activating Token Index: 693

Text #5

Max Range: 1.4929. Min Range: -1.4929

Max Act: 1.3294. Min Act: -0.0000

Data Index: 729321 (The Pile)

Max Activating Token Index: 97

Text #6

Max Range: 1.4929. Min Range: -1.4929

Max Act: 1.3841. Min Act: -0.0000

Data Index: 1144812 (The Pile)

Max Activating Token Index: 564

Text #7

Max Range: 1.4929. Min Range: -1.4929

Max Act: 1.2850. Min Act: -0.0000

Data Index: 1802463 (The Pile)

Max Activating Token Index: 9

Text #8

Max Range: 1.4929. Min Range: -1.4929

Max Act: 1.3672. Min Act: -0.0000

Data Index: 1256480 (The Pile)

Max Activating Token Index: 582

Text #9

Max Range: 1.4929. Min Range: -1.4929

Max Act: 1.2662. Min Act: -0.0000

Data Index: 131170 (The Pile)

Max Activating Token Index: 362

Text #10

Max Range: 1.4929. Min Range: -1.4929

Max Act: 1.3371. Min Act: -0.0000

Data Index: 832443 (The Pile)

Max Activating Token Index: 16

Text #11

Max Range: 1.4929. Min Range: -1.4929

Max Act: 1.2145. Min Act: -0.0000

Data Index: 506611 (The Pile)

Max Activating Token Index: 495

Text #12

Max Range: 1.4929. Min Range: -1.4929

Max Act: 1.1696. Min Act: -0.0000

Data Index: 551491 (The Pile)

Max Activating Token Index: 253

Text #13

Max Range: 1.4929. Min Range: -1.4929

Max Act: 1.3082. Min Act: -0.0000

Data Index: 1488345 (The Pile)

Max Activating Token Index: 553

Text #14

Max Range: 1.4929. Min Range: -1.4929

Max Act: 1.2001. Min Act: -0.0000

Data Index: 974859 (The Pile)

Max Activating Token Index: 159

Text #15

Max Range: 1.4929. Min Range: -1.4929

Max Act: 1.1894. Min Act: -0.0000

Data Index: 1550021 (The Pile)

Max Activating Token Index: 383

Text #16

Max Range: 1.4929. Min Range: -1.4929

Max Act: 1.1888. Min Act: -0.0000

Data Index: 1612573 (The Pile)

Max Activating Token Index: 322

Text #17

Max Range: 1.4929. Min Range: -1.4929

Max Act: 1.1836. Min Act: -0.0000

Data Index: 982922 (The Pile)

Max Activating Token Index: 385

Text #18

Max Range: 1.4929. Min Range: -1.4929

Max Act: 1.1039. Min Act: -0.0000

Data Index: 1396653 (The Pile)

Max Activating Token Index: 740

Text #19

Max Range: 1.4929. Min Range: -1.4929

Max Act: 1.3140. Min Act: -0.0000

Data Index: 663753 (The Pile)

Max Activating Token Index: 164