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

Dataset: The Pile

Neuron 1580 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: 0.8193. Min Range: -0.8193

Max Act: 0.7768. Min Act: -0.0000

Data Index: 1246262 (The Pile)

Max Activating Token Index: 906

Text #1

Max Range: 0.8193. Min Range: -0.8193

Max Act: 0.8193. Min Act: -0.0000

Data Index: 1138958 (The Pile)

Max Activating Token Index: 113

Text #2

Max Range: 0.8193. Min Range: -0.8193

Max Act: 0.7113. Min Act: -0.0000

Data Index: 479647 (The Pile)

Max Activating Token Index: 626

Text #3

Max Range: 0.8193. Min Range: -0.8193

Max Act: 0.7120. Min Act: -0.0000

Data Index: 751357 (The Pile)

Max Activating Token Index: 400

Text #4

Max Range: 0.8193. Min Range: -0.8193

Max Act: 0.7083. Min Act: -0.0000

Data Index: 961918 (The Pile)

Max Activating Token Index: 679

Text #5

Max Range: 0.8193. Min Range: -0.8193

Max Act: 0.7037. Min Act: -0.0000

Data Index: 1468494 (The Pile)

Max Activating Token Index: 209

Text #6

Max Range: 0.8193. Min Range: -0.8193

Max Act: 0.6800. Min Act: -0.0000

Data Index: 1969447 (The Pile)

Max Activating Token Index: 937

Text #7

Max Range: 0.8193. Min Range: -0.8193

Max Act: 0.6881. Min Act: -0.0000

Data Index: 1245885 (The Pile)

Max Activating Token Index: 679

Text #8

Max Range: 0.8193. Min Range: -0.8193

Max Act: 0.6952. Min Act: -0.0000

Data Index: 210077 (The Pile)

Max Activating Token Index: 390

Text #9

Max Range: 0.8193. Min Range: -0.8193

Max Act: 0.6486. Min Act: -0.0000

Data Index: 905786 (The Pile)

Max Activating Token Index: 336

Text #10

Max Range: 0.8193. Min Range: -0.8193

Max Act: 0.6976. Min Act: -0.0000

Data Index: 1270252 (The Pile)

Max Activating Token Index: 634

Text #11

Max Range: 0.8193. Min Range: -0.8193

Max Act: 0.6499. Min Act: -0.0000

Data Index: 780055 (The Pile)

Max Activating Token Index: 201

Text #12

Max Range: 0.8193. Min Range: -0.8193

Max Act: 0.6454. Min Act: -0.0000

Data Index: 1262770 (The Pile)

Max Activating Token Index: 947

Text #13

Max Range: 0.8193. Min Range: -0.8193

Max Act: 0.6484. Min Act: -0.0000

Data Index: 1081670 (The Pile)

Max Activating Token Index: 619

Text #14

Max Range: 0.8193. Min Range: -0.8193

Max Act: 0.7085. Min Act: -0.0000

Data Index: 558595 (The Pile)

Max Activating Token Index: 1018

Text #15

Max Range: 0.8193. Min Range: -0.8193

Max Act: 0.6074. Min Act: -0.0000

Data Index: 1770397 (The Pile)

Max Activating Token Index: 221

Text #16

Max Range: 0.8193. Min Range: -0.8193

Max Act: 0.6193. Min Act: -0.0000

Data Index: 1641735 (The Pile)

Max Activating Token Index: 80

Text #17

Max Range: 0.8193. Min Range: -0.8193

Max Act: 0.6392. Min Act: -0.0000

Data Index: 1171854 (The Pile)

Max Activating Token Index: 273

Text #18

Max Range: 0.8193. Min Range: -0.8193

Max Act: 0.6135. Min Act: -0.0000

Data Index: 363879 (The Pile)

Max Activating Token Index: 871

Text #19

Max Range: 0.8193. Min Range: -0.8193

Max Act: 0.5723. Min Act: -0.0000

Data Index: 1561075 (The Pile)

Max Activating Token Index: 701