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

Dataset: The Pile

Neuron 598 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.7638. Min Act: -0.0000

Data Index: 1918297 (The Pile)

Max Activating Token Index: 746

Text #1

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.6670. Min Act: -0.0000

Data Index: 3958 (The Pile)

Max Activating Token Index: 59

Text #2

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.7840. Min Act: -0.0000

Data Index: 1787145 (The Pile)

Max Activating Token Index: 868

Text #3

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.7150. Min Act: -0.0000

Data Index: 79078 (The Pile)

Max Activating Token Index: 143

Text #4

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.6813. Min Act: -0.0000

Data Index: 1158128 (The Pile)

Max Activating Token Index: 249

Text #5

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.6113. Min Act: -0.0000

Data Index: 1548625 (The Pile)

Max Activating Token Index: 185

Text #6

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.6079. Min Act: -0.0000

Data Index: 124797 (The Pile)

Max Activating Token Index: 477

Text #7

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.6283. Min Act: -0.0000

Data Index: 1601400 (The Pile)

Max Activating Token Index: 95

Text #8

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.5385. Min Act: -0.0000

Data Index: 788213 (The Pile)

Max Activating Token Index: 849

Text #9

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.5419. Min Act: -0.0000

Data Index: 1268398 (The Pile)

Max Activating Token Index: 889

Text #10

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.5782. Min Act: -0.0000

Data Index: 1827084 (The Pile)

Max Activating Token Index: 496

Text #11

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.5575. Min Act: -0.0000

Data Index: 1033194 (The Pile)

Max Activating Token Index: 1013

Text #12

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.5471. Min Act: -0.0000

Data Index: 1338143 (The Pile)

Max Activating Token Index: 484

Text #13

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.5132. Min Act: -0.0000

Data Index: 1372066 (The Pile)

Max Activating Token Index: 730

Text #14

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.5869. Min Act: -0.0000

Data Index: 1279739 (The Pile)

Max Activating Token Index: 745

Text #15

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.5237. Min Act: -0.0000

Data Index: 840198 (The Pile)

Max Activating Token Index: 716

Text #16

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.5283. Min Act: -0.0000

Data Index: 412877 (The Pile)

Max Activating Token Index: 168

Text #17

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.5260. Min Act: -0.0000

Data Index: 1583630 (The Pile)

Max Activating Token Index: 135

Text #18

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.4932. Min Act: -0.0000

Data Index: 1267108 (The Pile)

Max Activating Token Index: 544

Text #19

Max Range: 0.7840. Min Range: -0.7840

Max Act: 0.5402. Min Act: -0.0000

Data Index: 1738343 (The Pile)

Max Activating Token Index: 652