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

Dataset: The Pile

Neuron 2769 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.8092. Min Act: -0.0000

Data Index: 1836691 (The Pile)

Max Activating Token Index: 744

Text #1

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.7952. Min Act: -0.0000

Data Index: 466043 (The Pile)

Max Activating Token Index: 892

Text #2

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.9223. Min Act: -0.0000

Data Index: 1035743 (The Pile)

Max Activating Token Index: 552

Text #3

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6866. Min Act: -0.0000

Data Index: 1002975 (The Pile)

Max Activating Token Index: 634

Text #4

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6883. Min Act: -0.0000

Data Index: 1291358 (The Pile)

Max Activating Token Index: 181

Text #5

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6859. Min Act: -0.0000

Data Index: 1757020 (The Pile)

Max Activating Token Index: 322

Text #6

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6659. Min Act: -0.0000

Data Index: 1385857 (The Pile)

Max Activating Token Index: 279

Text #7

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6336. Min Act: -0.0000

Data Index: 1071209 (The Pile)

Max Activating Token Index: 711

Text #8

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6293. Min Act: -0.0000

Data Index: 1597382 (The Pile)

Max Activating Token Index: 937

Text #9

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6347. Min Act: -0.0000

Data Index: 1066747 (The Pile)

Max Activating Token Index: 216

Text #10

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.5919. Min Act: -0.0000

Data Index: 98687 (The Pile)

Max Activating Token Index: 842

Text #11

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6074. Min Act: -0.0000

Data Index: 162551 (The Pile)

Max Activating Token Index: 345

Text #12

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6670. Min Act: -0.0000

Data Index: 1691105 (The Pile)

Max Activating Token Index: 155

Text #13

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.5840. Min Act: -0.0000

Data Index: 1727838 (The Pile)

Max Activating Token Index: 138

Text #14

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6400. Min Act: -0.0000

Data Index: 1226891 (The Pile)

Max Activating Token Index: 100

Text #15

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6212. Min Act: -0.0000

Data Index: 1279740 (The Pile)

Max Activating Token Index: 186

Text #16

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6043. Min Act: -0.0000

Data Index: 173661 (The Pile)

Max Activating Token Index: 714

Text #17

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6060. Min Act: -0.0000

Data Index: 1753382 (The Pile)

Max Activating Token Index: 109

Text #18

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.5953. Min Act: -0.0000

Data Index: 1046323 (The Pile)

Max Activating Token Index: 516

Text #19

Max Range: 0.9223. Min Range: -0.9223

Max Act: 0.6017. Min Act: -0.0000

Data Index: 1139211 (The Pile)

Max Activating Token Index: 347