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

Dataset: The Pile

Neuron 3510 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.9841. Min Act: -0.0000

Data Index: 1136186 (The Pile)

Max Activating Token Index: 444

Text #1

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.9543. Min Act: -0.0000

Data Index: 1625966 (The Pile)

Max Activating Token Index: 727

Text #2

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.9310. Min Act: -0.0000

Data Index: 165721 (The Pile)

Max Activating Token Index: 920

Text #3

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.9751. Min Act: -0.0000

Data Index: 1549210 (The Pile)

Max Activating Token Index: 449

Text #4

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.9224. Min Act: -0.0000

Data Index: 658302 (The Pile)

Max Activating Token Index: 547

Text #5

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.9417. Min Act: -0.0000

Data Index: 554888 (The Pile)

Max Activating Token Index: 739

Text #6

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.9387. Min Act: -0.0000

Data Index: 1216826 (The Pile)

Max Activating Token Index: 469

Text #7

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.9583. Min Act: -0.0000

Data Index: 1254808 (The Pile)

Max Activating Token Index: 299

Text #8

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.9610. Min Act: -0.0000

Data Index: 1528502 (The Pile)

Max Activating Token Index: 812

Text #9

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.9269. Min Act: -0.0000

Data Index: 933078 (The Pile)

Max Activating Token Index: 83

Text #10

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.9250. Min Act: -0.0000

Data Index: 360368 (The Pile)

Max Activating Token Index: 655

Text #11

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.9189. Min Act: -0.0000

Data Index: 639962 (The Pile)

Max Activating Token Index: 570

Text #12

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.9186. Min Act: -0.0000

Data Index: 1166168 (The Pile)

Max Activating Token Index: 891

Text #13

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.9410. Min Act: -0.0000

Data Index: 156618 (The Pile)

Max Activating Token Index: 437

Text #14

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.8769. Min Act: -0.0000

Data Index: 1397648 (The Pile)

Max Activating Token Index: 806

Text #15

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.8836. Min Act: -0.0000

Data Index: 156613 (The Pile)

Max Activating Token Index: 926

Text #16

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.9143. Min Act: -0.0000

Data Index: 956500 (The Pile)

Max Activating Token Index: 972

Text #17

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.8801. Min Act: -0.0000

Data Index: 1256720 (The Pile)

Max Activating Token Index: 136

Text #18

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.8756. Min Act: -0.0000

Data Index: 241376 (The Pile)

Max Activating Token Index: 239

Text #19

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.8966. Min Act: -0.0000

Data Index: 878877 (The Pile)

Max Activating Token Index: 666