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

Dataset: The Pile

Neuron 2132 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.6757. Min Act: -0.0000

Data Index: 732706 (The Pile)

Max Activating Token Index: 84

Text #1

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.5725. Min Act: -0.0000

Data Index: 1956074 (The Pile)

Max Activating Token Index: 855

Text #2

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.5582. Min Act: -0.0000

Data Index: 1071444 (The Pile)

Max Activating Token Index: 377

Text #3

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.5215. Min Act: -0.0000

Data Index: 667367 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.5607. Min Act: -0.0000

Data Index: 751015 (The Pile)

Max Activating Token Index: 701

Text #5

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.5258. Min Act: -0.0000

Data Index: 1552654 (The Pile)

Max Activating Token Index: 52

Text #6

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.5350. Min Act: -0.0000

Data Index: 1628922 (The Pile)

Max Activating Token Index: 722

Text #7

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.5290. Min Act: -0.0000

Data Index: 1289098 (The Pile)

Max Activating Token Index: 873

Text #8

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.5298. Min Act: -0.0000

Data Index: 1088085 (The Pile)

Max Activating Token Index: 181

Text #9

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.5108. Min Act: -0.0000

Data Index: 1952175 (The Pile)

Max Activating Token Index: 240

Text #10

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4755. Min Act: -0.0000

Data Index: 150176 (The Pile)

Max Activating Token Index: 282

Text #11

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4684. Min Act: -0.0000

Data Index: 1895594 (The Pile)

Max Activating Token Index: 190

Text #12

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4859. Min Act: -0.0000

Data Index: 1672753 (The Pile)

Max Activating Token Index: 109

Text #13

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4596. Min Act: -0.0000

Data Index: 1847076 (The Pile)

Max Activating Token Index: 258

Text #14

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4463. Min Act: -0.0000

Data Index: 953524 (The Pile)

Max Activating Token Index: 546

Text #15

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4453. Min Act: -0.0000

Data Index: 883189 (The Pile)

Max Activating Token Index: 523

Text #16

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.3456. Min Act: -0.0000

Data Index: 164427 (The Pile)

Max Activating Token Index: 789

Text #17

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4557. Min Act: -0.0000

Data Index: 138934 (The Pile)

Max Activating Token Index: 151

Text #18

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4164. Min Act: -0.0000

Data Index: 141201 (The Pile)

Max Activating Token Index: 991

Text #19

Max Range: 0.6757. Min Range: -0.6757

Max Act: 0.4063. Min Act: -0.0000

Data Index: 505612 (The Pile)

Max Activating Token Index: 951