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

Dataset: The Pile

Neuron 3313 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: 1.5457. Min Range: -1.5457

Max Act: 1.3949. Min Act: -0.0000

Data Index: 111968 (The Pile)

Max Activating Token Index: 114

Text #1

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.3583. Min Act: -0.0000

Data Index: 935769 (The Pile)

Max Activating Token Index: 115

Text #2

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.3296. Min Act: -0.0000

Data Index: 1585170 (The Pile)

Max Activating Token Index: 775

Text #3

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.3817. Min Act: -0.0000

Data Index: 1411360 (The Pile)

Max Activating Token Index: 127

Text #4

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.3559. Min Act: -0.0000

Data Index: 1796452 (The Pile)

Max Activating Token Index: 732

Text #5

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.3570. Min Act: -0.0000

Data Index: 1412691 (The Pile)

Max Activating Token Index: 92

Text #6

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.5457. Min Act: -0.0000

Data Index: 304126 (The Pile)

Max Activating Token Index: 103

Text #7

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.3808. Min Act: -0.0000

Data Index: 646937 (The Pile)

Max Activating Token Index: 105

Text #8

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.3984. Min Act: -0.0000

Data Index: 1526667 (The Pile)

Max Activating Token Index: 105

Text #9

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.4448. Min Act: -0.0000

Data Index: 613177 (The Pile)

Max Activating Token Index: 100

Text #10

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.4468. Min Act: -0.0000

Data Index: 706033 (The Pile)

Max Activating Token Index: 742

Text #11

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.4542. Min Act: -0.0000

Data Index: 459677 (The Pile)

Max Activating Token Index: 87

Text #12

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.3297. Min Act: -0.0000

Data Index: 678748 (The Pile)

Max Activating Token Index: 136

Text #13

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.3123. Min Act: -0.0000

Data Index: 1506404 (The Pile)

Max Activating Token Index: 97

Text #14

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.3009. Min Act: -0.0000

Data Index: 378788 (The Pile)

Max Activating Token Index: 120

Text #15

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.4126. Min Act: -0.0000

Data Index: 1768062 (The Pile)

Max Activating Token Index: 314

Text #16

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.3923. Min Act: -0.0000

Data Index: 1726927 (The Pile)

Max Activating Token Index: 102

Text #17

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.1615. Min Act: -0.0000

Data Index: 185771 (The Pile)

Max Activating Token Index: 758

Text #18

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.3072. Min Act: -0.0000

Data Index: 232241 (The Pile)

Max Activating Token Index: 143

Text #19

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.2607. Min Act: -0.0000

Data Index: 648044 (The Pile)

Max Activating Token Index: 270