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

Dataset: The Pile

Neuron 4548 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: 1.6101. Min Range: -1.6101

Max Act: 1.6101. Min Act: -0.0000

Data Index: 1268757 (The Pile)

Max Activating Token Index: 809

Text #1

Max Range: 1.6101. Min Range: -1.6101

Max Act: 1.4673. Min Act: -0.0000

Data Index: 406785 (The Pile)

Max Activating Token Index: 180

Text #2

Max Range: 1.6101. Min Range: -1.6101

Max Act: 1.5170. Min Act: -0.0000

Data Index: 538658 (The Pile)

Max Activating Token Index: 529

Text #3

Max Range: 1.6101. Min Range: -1.6101

Max Act: 1.5092. Min Act: -0.0000

Data Index: 1454896 (The Pile)

Max Activating Token Index: 29

Text #4

Max Range: 1.6101. Min Range: -1.6101

Max Act: 1.2579. Min Act: -0.0000

Data Index: 1283801 (The Pile)

Max Activating Token Index: 718

Text #5

Max Range: 1.6101. Min Range: -1.6101

Max Act: 1.2189. Min Act: -0.0000

Data Index: 621468 (The Pile)

Max Activating Token Index: 114

Text #6

Max Range: 1.6101. Min Range: -1.6101

Max Act: 1.1923. Min Act: -0.0000

Data Index: 1293535 (The Pile)

Max Activating Token Index: 968

Text #7

Max Range: 1.6101. Min Range: -1.6101

Max Act: 1.1230. Min Act: -0.0000

Data Index: 1683025 (The Pile)

Max Activating Token Index: 36

Text #8

Max Range: 1.6101. Min Range: -1.6101

Max Act: 1.1773. Min Act: -0.0000

Data Index: 1088301 (The Pile)

Max Activating Token Index: 593

Text #9

Max Range: 1.6101. Min Range: -1.6101

Max Act: 1.1680. Min Act: -0.0000

Data Index: 514417 (The Pile)

Max Activating Token Index: 840

Text #10

Max Range: 1.6101. Min Range: -1.6101

Max Act: 1.0811. Min Act: -0.0000

Data Index: 952132 (The Pile)

Max Activating Token Index: 1009

Text #11

Max Range: 1.6101. Min Range: -1.6101

Max Act: 1.1428. Min Act: -0.0000

Data Index: 1845827 (The Pile)

Max Activating Token Index: 1021

Text #12

Max Range: 1.6101. Min Range: -1.6101

Max Act: 1.1082. Min Act: -0.0000

Data Index: 1460023 (The Pile)

Max Activating Token Index: 447

Text #13

Max Range: 1.6101. Min Range: -1.6101

Max Act: 1.0722. Min Act: -0.0000

Data Index: 1913675 (The Pile)

Max Activating Token Index: 204

Text #14

Max Range: 1.6101. Min Range: -1.6101

Max Act: 1.0787. Min Act: -0.0000

Data Index: 1441137 (The Pile)

Max Activating Token Index: 223

Text #15

Max Range: 1.6101. Min Range: -1.6101

Max Act: 1.1965. Min Act: -0.0000

Data Index: 576749 (The Pile)

Max Activating Token Index: 251

Text #16

Max Range: 1.6101. Min Range: -1.6101

Max Act: 1.0018. Min Act: 0.0000

Data Index: 1919734 (The Pile)

Max Activating Token Index: 38

Text #17

Max Range: 1.6101. Min Range: -1.6101

Max Act: 1.0975. Min Act: -0.0000

Data Index: 389845 (The Pile)

Max Activating Token Index: 756

Text #18

Max Range: 1.6101. Min Range: -1.6101

Max Act: 0.9828. Min Act: -0.0000

Data Index: 103195 (The Pile)

Max Activating Token Index: 1009

Text #19

Max Range: 1.6101. Min Range: -1.6101

Max Act: 1.0372. Min Act: -0.0000

Data Index: 545510 (The Pile)

Max Activating Token Index: 964