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

Dataset: The Pile

Neuron 1796 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5585. Min Range: -1.5585

Max Act: 1.5585. Min Act: -0.0000

Data Index: 1529606 (The Pile)

Max Activating Token Index: 49

Text #1

Max Range: 1.5585. Min Range: -1.5585

Max Act: 1.0263. Min Act: -0.0000

Data Index: 717437 (The Pile)

Max Activating Token Index: 190

Text #2

Max Range: 1.5585. Min Range: -1.5585

Max Act: 0.8150. Min Act: -0.0000

Data Index: 1537377 (The Pile)

Max Activating Token Index: 962

Text #3

Max Range: 1.5585. Min Range: -1.5585

Max Act: 0.7724. Min Act: -0.0000

Data Index: 1898723 (The Pile)

Max Activating Token Index: 779

Text #4

Max Range: 1.5585. Min Range: -1.5585

Max Act: 0.7821. Min Act: -0.0000

Data Index: 860094 (The Pile)

Max Activating Token Index: 774

Text #5

Max Range: 1.5585. Min Range: -1.5585

Max Act: 0.7721. Min Act: -0.0000

Data Index: 1879999 (The Pile)

Max Activating Token Index: 682

Text #6

Max Range: 1.5585. Min Range: -1.5585

Max Act: 0.7122. Min Act: -0.0000

Data Index: 1301836 (The Pile)

Max Activating Token Index: 927

Text #7

Max Range: 1.5585. Min Range: -1.5585

Max Act: 0.6976. Min Act: -0.0000

Data Index: 1211388 (The Pile)

Max Activating Token Index: 300

Text #8

Max Range: 1.5585. Min Range: -1.5585

Max Act: 0.7303. Min Act: -0.0000

Data Index: 1045364 (The Pile)

Max Activating Token Index: 123

Text #9

Max Range: 1.5585. Min Range: -1.5585

Max Act: 0.7682. Min Act: -0.0000

Data Index: 478948 (The Pile)

Max Activating Token Index: 660

Text #10

Max Range: 1.5585. Min Range: -1.5585

Max Act: 0.7302. Min Act: -0.0000

Data Index: 1145969 (The Pile)

Max Activating Token Index: 635

Text #11

Max Range: 1.5585. Min Range: -1.5585

Max Act: 0.6935. Min Act: -0.0000

Data Index: 1374014 (The Pile)

Max Activating Token Index: 1016

Text #12

Max Range: 1.5585. Min Range: -1.5585

Max Act: 0.6536. Min Act: -0.0000

Data Index: 1280893 (The Pile)

Max Activating Token Index: 1001

Text #13

Max Range: 1.5585. Min Range: -1.5585

Max Act: 0.7515. Min Act: -0.0000

Data Index: 620255 (The Pile)

Max Activating Token Index: 9

Text #14

Max Range: 1.5585. Min Range: -1.5585

Max Act: 0.7693. Min Act: -0.0000

Data Index: 157195 (The Pile)

Max Activating Token Index: 332

Text #15

Max Range: 1.5585. Min Range: -1.5585

Max Act: 0.7287. Min Act: 0.0000

Data Index: 187435 (The Pile)

Max Activating Token Index: 608

Text #16

Max Range: 1.5585. Min Range: -1.5585

Max Act: 0.6922. Min Act: -0.0000

Data Index: 704788 (The Pile)

Max Activating Token Index: 82

Text #17

Max Range: 1.5585. Min Range: -1.5585

Max Act: 0.7069. Min Act: 0.0001

Data Index: 27566 (The Pile)

Max Activating Token Index: 83

Text #18

Max Range: 1.5585. Min Range: -1.5585

Max Act: 0.6838. Min Act: -0.0000

Data Index: 259243 (The Pile)

Max Activating Token Index: 195

Text #19

Max Range: 1.5585. Min Range: -1.5585

Max Act: 0.6934. Min Act: -0.0000

Data Index: 1798054 (The Pile)

Max Activating Token Index: 968