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

Dataset: The Pile

Neuron 3458 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.5618. Min Act: -0.0000

Data Index: 217730 (The Pile)

Max Activating Token Index: 651

Text #1

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.6051. Min Act: -0.0000

Data Index: 1278703 (The Pile)

Max Activating Token Index: 897

Text #2

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.6060. Min Act: 0.0000

Data Index: 1078302 (The Pile)

Max Activating Token Index: 328

Text #3

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4943. Min Act: -0.0000

Data Index: 22643 (The Pile)

Max Activating Token Index: 459

Text #4

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4999. Min Act: -0.0000

Data Index: 1652810 (The Pile)

Max Activating Token Index: 326

Text #5

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4763. Min Act: -0.0000

Data Index: 1852417 (The Pile)

Max Activating Token Index: 991

Text #6

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4738. Min Act: -0.0000

Data Index: 343107 (The Pile)

Max Activating Token Index: 584

Text #7

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4586. Min Act: -0.0000

Data Index: 1386592 (The Pile)

Max Activating Token Index: 128

Text #8

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4267. Min Act: 0.0000

Data Index: 190657 (The Pile)

Max Activating Token Index: 718

Text #9

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4441. Min Act: -0.0000

Data Index: 159411 (The Pile)

Max Activating Token Index: 153

Text #10

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4241. Min Act: -0.0000

Data Index: 1198694 (The Pile)

Max Activating Token Index: 162

Text #11

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4288. Min Act: -0.0000

Data Index: 1021814 (The Pile)

Max Activating Token Index: 888

Text #12

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.3937. Min Act: -0.0000

Data Index: 1577865 (The Pile)

Max Activating Token Index: 44

Text #13

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4264. Min Act: 0.0000

Data Index: 590070 (The Pile)

Max Activating Token Index: 904

Text #14

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4246. Min Act: -0.0000

Data Index: 906662 (The Pile)

Max Activating Token Index: 826

Text #15

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.3829. Min Act: -0.0000

Data Index: 781829 (The Pile)

Max Activating Token Index: 984

Text #16

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.3898. Min Act: -0.0000

Data Index: 275482 (The Pile)

Max Activating Token Index: 149

Text #17

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.4285. Min Act: -0.0000

Data Index: 883829 (The Pile)

Max Activating Token Index: 558

Text #18

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.3999. Min Act: 0.0000

Data Index: 1766063 (The Pile)

Max Activating Token Index: 268

Text #19

Max Range: 0.6060. Min Range: -0.6060

Max Act: 0.3998. Min Act: -0.0000

Data Index: 1407995 (The Pile)

Max Activating Token Index: 302