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

Dataset: The Pile

Neuron 335 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: 0.6101. Min Range: -0.6101

Max Act: 0.6101. Min Act: -0.0000

Data Index: 1530477 (The Pile)

Max Activating Token Index: 681

Text #1

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.6096. Min Act: -0.0000

Data Index: 226218 (The Pile)

Max Activating Token Index: 560

Text #2

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.6009. Min Act: -0.0000

Data Index: 131335 (The Pile)

Max Activating Token Index: 878

Text #3

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.5562. Min Act: -0.0000

Data Index: 1797938 (The Pile)

Max Activating Token Index: 711

Text #4

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.5658. Min Act: -0.0000

Data Index: 873862 (The Pile)

Max Activating Token Index: 17

Text #5

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.5257. Min Act: -0.0000

Data Index: 736796 (The Pile)

Max Activating Token Index: 495

Text #6

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.5377. Min Act: -0.0000

Data Index: 1355413 (The Pile)

Max Activating Token Index: 808

Text #7

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.5060. Min Act: -0.0000

Data Index: 1410203 (The Pile)

Max Activating Token Index: 354

Text #8

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.4848. Min Act: -0.0000

Data Index: 1511317 (The Pile)

Max Activating Token Index: 949

Text #9

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.5198. Min Act: -0.0000

Data Index: 858469 (The Pile)

Max Activating Token Index: 700

Text #10

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.5028. Min Act: -0.0000

Data Index: 1026713 (The Pile)

Max Activating Token Index: 41

Text #11

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.5184. Min Act: -0.0000

Data Index: 1787550 (The Pile)

Max Activating Token Index: 114

Text #12

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.5005. Min Act: -0.0000

Data Index: 200909 (The Pile)

Max Activating Token Index: 534

Text #13

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.4803. Min Act: -0.0000

Data Index: 828288 (The Pile)

Max Activating Token Index: 58

Text #14

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.5093. Min Act: -0.0000

Data Index: 865567 (The Pile)

Max Activating Token Index: 325

Text #15

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.5244. Min Act: -0.0000

Data Index: 1817709 (The Pile)

Max Activating Token Index: 469

Text #16

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.4774. Min Act: -0.0000

Data Index: 1293916 (The Pile)

Max Activating Token Index: 937

Text #17

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.4918. Min Act: -0.0000

Data Index: 52994 (The Pile)

Max Activating Token Index: 225

Text #18

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.5189. Min Act: -0.0000

Data Index: 1635212 (The Pile)

Max Activating Token Index: 927

Text #19

Max Range: 0.6101. Min Range: -0.6101

Max Act: 0.5033. Min Act: -0.0000

Data Index: 1513263 (The Pile)

Max Activating Token Index: 811