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

Dataset: The Pile

Neuron 2839 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: 1.1557. Min Range: -1.1557

Max Act: 1.1036. Min Act: -0.0000

Data Index: 1291116 (The Pile)

Max Activating Token Index: 36

Text #1

Max Range: 1.1557. Min Range: -1.1557

Max Act: 1.1557. Min Act: -0.0000

Data Index: 90826 (The Pile)

Max Activating Token Index: 679

Text #2

Max Range: 1.1557. Min Range: -1.1557

Max Act: 1.0750. Min Act: -0.0000

Data Index: 1033270 (The Pile)

Max Activating Token Index: 141

Text #3

Max Range: 1.1557. Min Range: -1.1557

Max Act: 1.0275. Min Act: -0.0000

Data Index: 1288062 (The Pile)

Max Activating Token Index: 53

Text #4

Max Range: 1.1557. Min Range: -1.1557

Max Act: 0.9462. Min Act: -0.0000

Data Index: 1225932 (The Pile)

Max Activating Token Index: 914

Text #5

Max Range: 1.1557. Min Range: -1.1557

Max Act: 1.0148. Min Act: -0.0000

Data Index: 1496608 (The Pile)

Max Activating Token Index: 933

Text #6

Max Range: 1.1557. Min Range: -1.1557

Max Act: 1.0092. Min Act: -0.0000

Data Index: 1683014 (The Pile)

Max Activating Token Index: 466

Text #7

Max Range: 1.1557. Min Range: -1.1557

Max Act: 0.9468. Min Act: -0.0000

Data Index: 77141 (The Pile)

Max Activating Token Index: 180

Text #8

Max Range: 1.1557. Min Range: -1.1557

Max Act: 1.0107. Min Act: -0.0000

Data Index: 675221 (The Pile)

Max Activating Token Index: 43

Text #9

Max Range: 1.1557. Min Range: -1.1557

Max Act: 0.9638. Min Act: -0.0000

Data Index: 1209416 (The Pile)

Max Activating Token Index: 171

Text #10

Max Range: 1.1557. Min Range: -1.1557

Max Act: 0.9562. Min Act: -0.0000

Data Index: 180671 (The Pile)

Max Activating Token Index: 334

Text #11

Max Range: 1.1557. Min Range: -1.1557

Max Act: 0.9563. Min Act: -0.0000

Data Index: 1650819 (The Pile)

Max Activating Token Index: 7

Text #12

Max Range: 1.1557. Min Range: -1.1557

Max Act: 0.9066. Min Act: -0.0000

Data Index: 167183 (The Pile)

Max Activating Token Index: 137

Text #13

Max Range: 1.1557. Min Range: -1.1557

Max Act: 0.8825. Min Act: -0.0000

Data Index: 1138316 (The Pile)

Max Activating Token Index: 971

Text #14

Max Range: 1.1557. Min Range: -1.1557

Max Act: 0.8220. Min Act: -0.0000

Data Index: 264712 (The Pile)

Max Activating Token Index: 816

Text #15

Max Range: 1.1557. Min Range: -1.1557

Max Act: 0.9029. Min Act: -0.0000

Data Index: 1166453 (The Pile)

Max Activating Token Index: 394

Text #16

Max Range: 1.1557. Min Range: -1.1557

Max Act: 0.8835. Min Act: -0.0000

Data Index: 362158 (The Pile)

Max Activating Token Index: 207

Text #17

Max Range: 1.1557. Min Range: -1.1557

Max Act: 0.8993. Min Act: -0.0000

Data Index: 234615 (The Pile)

Max Activating Token Index: 30

Text #18

Max Range: 1.1557. Min Range: -1.1557

Max Act: 0.8700. Min Act: -0.0000

Data Index: 1603705 (The Pile)

Max Activating Token Index: 409

Text #19

Max Range: 1.1557. Min Range: -1.1557

Max Act: 0.8423. Min Act: -0.0000

Data Index: 1080734 (The Pile)

Max Activating Token Index: 570