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

Dataset: The Pile

Neuron 4845 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.1024. Min Act: -0.0001

Data Index: 1651558 (The Pile)

Max Activating Token Index: 13

Text #1

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.1004. Min Act: -0.0001

Data Index: 1932465 (The Pile)

Max Activating Token Index: 230

Text #2

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0915. Min Act: -0.0001

Data Index: 281232 (The Pile)

Max Activating Token Index: 293

Text #3

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0739. Min Act: -0.0001

Data Index: 409611 (The Pile)

Max Activating Token Index: 114

Text #4

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0760. Min Act: -0.0001

Data Index: 1274164 (The Pile)

Max Activating Token Index: 258

Text #5

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0744. Min Act: -0.0001

Data Index: 548342 (The Pile)

Max Activating Token Index: 409

Text #6

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0769. Min Act: -0.0001

Data Index: 532363 (The Pile)

Max Activating Token Index: 222

Text #7

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0764. Min Act: -0.0001

Data Index: 245379 (The Pile)

Max Activating Token Index: 55

Text #8

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0752. Min Act: -0.0001

Data Index: 1745893 (The Pile)

Max Activating Token Index: 370

Text #9

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0721. Min Act: -0.0001

Data Index: 90231 (The Pile)

Max Activating Token Index: 392

Text #10

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0744. Min Act: -0.0001

Data Index: 1684366 (The Pile)

Max Activating Token Index: 222

Text #11

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0716. Min Act: -0.0001

Data Index: 427846 (The Pile)

Max Activating Token Index: 595

Text #12

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0744. Min Act: -0.0001

Data Index: 1705521 (The Pile)

Max Activating Token Index: 552

Text #13

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0675. Min Act: -0.0001

Data Index: 679427 (The Pile)

Max Activating Token Index: 845

Text #14

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0690. Min Act: -0.0001

Data Index: 1665037 (The Pile)

Max Activating Token Index: 841

Text #15

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0699. Min Act: -0.0001

Data Index: 1804139 (The Pile)

Max Activating Token Index: 274

Text #16

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0691. Min Act: -0.0001

Data Index: 403414 (The Pile)

Max Activating Token Index: 141

Text #17

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0662. Min Act: -0.0001

Data Index: 408966 (The Pile)

Max Activating Token Index: 728

Text #18

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0736. Min Act: -0.0001

Data Index: 1415374 (The Pile)

Max Activating Token Index: 855

Text #19

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0625. Min Act: -0.0001

Data Index: 886003 (The Pile)

Max Activating Token Index: 1005