Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3401 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.7818. Min Range: -1.7818

Max Act: 1.7818. Min Act: -0.0000

Data Index: 1331995 (The Pile)

Max Activating Token Index: 579

Text #1

Max Range: 1.7818. Min Range: -1.7818

Max Act: 1.5765. Min Act: -0.0000

Data Index: 1321071 (The Pile)

Max Activating Token Index: 78

Text #2

Max Range: 1.7818. Min Range: -1.7818

Max Act: 1.5987. Min Act: -0.0000

Data Index: 682782 (The Pile)

Max Activating Token Index: 831

Text #3

Max Range: 1.7818. Min Range: -1.7818

Max Act: 0.8570. Min Act: -0.0000

Data Index: 1157492 (The Pile)

Max Activating Token Index: 675

Text #4

Max Range: 1.7818. Min Range: -1.7818

Max Act: 1.1039. Min Act: -0.0000

Data Index: 934307 (The Pile)

Max Activating Token Index: 32

Text #5

Max Range: 1.7818. Min Range: -1.7818

Max Act: 0.5448. Min Act: -0.0000

Data Index: 739511 (The Pile)

Max Activating Token Index: 767

Text #6

Max Range: 1.7818. Min Range: -1.7818

Max Act: 1.0843. Min Act: -0.0000

Data Index: 1553229 (The Pile)

Max Activating Token Index: 716

Text #7

Max Range: 1.7818. Min Range: -1.7818

Max Act: 0.6008. Min Act: -0.0000

Data Index: 734239 (The Pile)

Max Activating Token Index: 32

Text #8

Max Range: 1.7818. Min Range: -1.7818

Max Act: 0.5113. Min Act: -0.0000

Data Index: 1717178 (The Pile)

Max Activating Token Index: 113

Text #9

Max Range: 1.7818. Min Range: -1.7818

Max Act: 0.7130. Min Act: -0.0000

Data Index: 1077771 (The Pile)

Max Activating Token Index: 649

Text #10

Max Range: 1.7818. Min Range: -1.7818

Max Act: 0.4126. Min Act: -0.0000

Data Index: 666783 (The Pile)

Max Activating Token Index: 648

Text #11

Max Range: 1.7818. Min Range: -1.7818

Max Act: 0.7970. Min Act: -0.0000

Data Index: 875881 (The Pile)

Max Activating Token Index: 114

Text #12

Max Range: 1.7818. Min Range: -1.7818

Max Act: 1.4593. Min Act: -0.0000

Data Index: 987934 (The Pile)

Max Activating Token Index: 117

Text #13

Max Range: 1.7818. Min Range: -1.7818

Max Act: 0.7245. Min Act: -0.0000

Data Index: 1480301 (The Pile)

Max Activating Token Index: 463

Text #14

Max Range: 1.7818. Min Range: -1.7818

Max Act: 0.6519. Min Act: -0.0000

Data Index: 205761 (The Pile)

Max Activating Token Index: 632

Text #15

Max Range: 1.7818. Min Range: -1.7818

Max Act: 0.4038. Min Act: -0.0000

Data Index: 206909 (The Pile)

Max Activating Token Index: 640

Text #16

Max Range: 1.7818. Min Range: -1.7818

Max Act: 0.4964. Min Act: -0.0000

Data Index: 1760900 (The Pile)

Max Activating Token Index: 198

Text #17

Max Range: 1.7818. Min Range: -1.7818

Max Act: 0.5902. Min Act: -0.0000

Data Index: 1873746 (The Pile)

Max Activating Token Index: 736

Text #18

Max Range: 1.7818. Min Range: -1.7818

Max Act: 0.6407. Min Act: -0.0000

Data Index: 761795 (The Pile)

Max Activating Token Index: 177

Text #19

Max Range: 1.7818. Min Range: -1.7818

Max Act: 0.4426. Min Act: -0.0000

Data Index: 21276 (The Pile)

Max Activating Token Index: 579