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

Dataset: The Pile

Neuron 4022 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: 1.7936. Min Range: -1.7936

Max Act: 1.7936. Min Act: -0.0000

Data Index: 1675613 (The Pile)

Max Activating Token Index: 20

Text #1

Max Range: 1.7936. Min Range: -1.7936

Max Act: 1.6793. Min Act: -0.0000

Data Index: 217016 (The Pile)

Max Activating Token Index: 582

Text #2

Max Range: 1.7936. Min Range: -1.7936

Max Act: 1.7577. Min Act: -0.0000

Data Index: 72400 (The Pile)

Max Activating Token Index: 1018

Text #3

Max Range: 1.7936. Min Range: -1.7936

Max Act: 1.4917. Min Act: -0.0000

Data Index: 342740 (The Pile)

Max Activating Token Index: 784

Text #4

Max Range: 1.7936. Min Range: -1.7936

Max Act: 1.4822. Min Act: -0.0000

Data Index: 1039000 (The Pile)

Max Activating Token Index: 374

Text #5

Max Range: 1.7936. Min Range: -1.7936

Max Act: 1.4800. Min Act: -0.0000

Data Index: 341504 (The Pile)

Max Activating Token Index: 680

Text #6

Max Range: 1.7936. Min Range: -1.7936

Max Act: 1.5644. Min Act: -0.0000

Data Index: 1451838 (The Pile)

Max Activating Token Index: 69

Text #7

Max Range: 1.7936. Min Range: -1.7936

Max Act: 1.4740. Min Act: -0.0000

Data Index: 276539 (The Pile)

Max Activating Token Index: 34

Text #8

Max Range: 1.7936. Min Range: -1.7936

Max Act: 1.5465. Min Act: -0.0000

Data Index: 333520 (The Pile)

Max Activating Token Index: 961

Text #9

Max Range: 1.7936. Min Range: -1.7936

Max Act: 1.3764. Min Act: -0.0000

Data Index: 81747 (The Pile)

Max Activating Token Index: 813

Text #10

Max Range: 1.7936. Min Range: -1.7936

Max Act: 1.3805. Min Act: -0.0000

Data Index: 1230013 (The Pile)

Max Activating Token Index: 1004

Text #11

Max Range: 1.7936. Min Range: -1.7936

Max Act: 1.4024. Min Act: -0.0000

Data Index: 1816639 (The Pile)

Max Activating Token Index: 1018

Text #12

Max Range: 1.7936. Min Range: -1.7936

Max Act: 1.3607. Min Act: -0.0000

Data Index: 1416723 (The Pile)

Max Activating Token Index: 825

Text #13

Max Range: 1.7936. Min Range: -1.7936

Max Act: 1.4868. Min Act: -0.0000

Data Index: 1995092 (The Pile)

Max Activating Token Index: 20

Text #14

Max Range: 1.7936. Min Range: -1.7936

Max Act: 1.3954. Min Act: -0.0000

Data Index: 130559 (The Pile)

Max Activating Token Index: 987

Text #15

Max Range: 1.7936. Min Range: -1.7936

Max Act: 1.4153. Min Act: -0.0000

Data Index: 1735503 (The Pile)

Max Activating Token Index: 94

Text #16

Max Range: 1.7936. Min Range: -1.7936

Max Act: 1.3696. Min Act: -0.0000

Data Index: 1486294 (The Pile)

Max Activating Token Index: 464

Text #17

Max Range: 1.7936. Min Range: -1.7936

Max Act: 1.4134. Min Act: -0.0000

Data Index: 1852327 (The Pile)

Max Activating Token Index: 35

Text #18

Max Range: 1.7936. Min Range: -1.7936

Max Act: 1.4362. Min Act: -0.0000

Data Index: 543005 (The Pile)

Max Activating Token Index: 958

Text #19

Max Range: 1.7936. Min Range: -1.7936

Max Act: 1.3256. Min Act: -0.0000

Data Index: 796802 (The Pile)

Max Activating Token Index: 264