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

Dataset: The Pile

Neuron 4181 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: 1.8900. Min Range: -1.8900

Max Act: 1.8900. Min Act: -0.0000

Data Index: 1366724 (The Pile)

Max Activating Token Index: 834

Text #1

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.7679. Min Act: -0.0000

Data Index: 1333750 (The Pile)

Max Activating Token Index: 271

Text #2

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.7238. Min Act: -0.0000

Data Index: 355959 (The Pile)

Max Activating Token Index: 773

Text #3

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.7160. Min Act: -0.0000

Data Index: 1735296 (The Pile)

Max Activating Token Index: 1001

Text #4

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.6725. Min Act: -0.0000

Data Index: 552663 (The Pile)

Max Activating Token Index: 746

Text #5

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.8350. Min Act: -0.0000

Data Index: 1891844 (The Pile)

Max Activating Token Index: 179

Text #6

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.5717. Min Act: -0.0000

Data Index: 1716024 (The Pile)

Max Activating Token Index: 1015

Text #7

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.4731. Min Act: -0.0000

Data Index: 481789 (The Pile)

Max Activating Token Index: 876

Text #8

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.7211. Min Act: -0.0000

Data Index: 1110003 (The Pile)

Max Activating Token Index: 825

Text #9

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.6404. Min Act: -0.0000

Data Index: 1450505 (The Pile)

Max Activating Token Index: 262

Text #10

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.6106. Min Act: -0.0000

Data Index: 1265055 (The Pile)

Max Activating Token Index: 124

Text #11

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.4963. Min Act: -0.0000

Data Index: 299115 (The Pile)

Max Activating Token Index: 671

Text #12

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.5827. Min Act: -0.0000

Data Index: 1692101 (The Pile)

Max Activating Token Index: 543

Text #13

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.3995. Min Act: -0.0000

Data Index: 1385124 (The Pile)

Max Activating Token Index: 734

Text #14

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.7112. Min Act: -0.0000

Data Index: 1749787 (The Pile)

Max Activating Token Index: 790

Text #15

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.6087. Min Act: -0.0000

Data Index: 176690 (The Pile)

Max Activating Token Index: 734

Text #16

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.5248. Min Act: -0.0000

Data Index: 682638 (The Pile)

Max Activating Token Index: 649

Text #17

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.5098. Min Act: -0.0000

Data Index: 668298 (The Pile)

Max Activating Token Index: 98

Text #18

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.3672. Min Act: -0.0000

Data Index: 149877 (The Pile)

Max Activating Token Index: 117

Text #19

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.4291. Min Act: -0.0000

Data Index: 869333 (The Pile)

Max Activating Token Index: 880