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

Dataset: The Pile

Neuron 1291 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: 1.3708. Min Range: -1.3708

Max Act: 1.3708. Min Act: -0.0000

Data Index: 742965 (The Pile)

Max Activating Token Index: 46

Text #1

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.2998. Min Act: -0.0000

Data Index: 519833 (The Pile)

Max Activating Token Index: 627

Text #2

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.2330. Min Act: -0.0000

Data Index: 982867 (The Pile)

Max Activating Token Index: 303

Text #3

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.0607. Min Act: -0.0000

Data Index: 778016 (The Pile)

Max Activating Token Index: 738

Text #4

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.1302. Min Act: -0.0000

Data Index: 1859864 (The Pile)

Max Activating Token Index: 711

Text #5

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.0678. Min Act: -0.0000

Data Index: 1216592 (The Pile)

Max Activating Token Index: 647

Text #6

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.1326. Min Act: -0.0000

Data Index: 1482445 (The Pile)

Max Activating Token Index: 22

Text #7

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.1415. Min Act: -0.0000

Data Index: 701332 (The Pile)

Max Activating Token Index: 424

Text #8

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.3107. Min Act: -0.0000

Data Index: 735140 (The Pile)

Max Activating Token Index: 760

Text #9

Max Range: 1.3708. Min Range: -1.3708

Max Act: 0.9540. Min Act: -0.0000

Data Index: 1634004 (The Pile)

Max Activating Token Index: 150

Text #10

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.1072. Min Act: -0.0000

Data Index: 1174603 (The Pile)

Max Activating Token Index: 150

Text #11

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.1659. Min Act: -0.0000

Data Index: 1257698 (The Pile)

Max Activating Token Index: 73

Text #12

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.0633. Min Act: -0.0000

Data Index: 1293235 (The Pile)

Max Activating Token Index: 884

Text #13

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.1474. Min Act: -0.0000

Data Index: 437383 (The Pile)

Max Activating Token Index: 442

Text #14

Max Range: 1.3708. Min Range: -1.3708

Max Act: 0.9924. Min Act: -0.0000

Data Index: 204459 (The Pile)

Max Activating Token Index: 91

Text #15

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.0678. Min Act: -0.0000

Data Index: 688619 (The Pile)

Max Activating Token Index: 877

Text #16

Max Range: 1.3708. Min Range: -1.3708

Max Act: 1.0252. Min Act: -0.0000

Data Index: 1320815 (The Pile)

Max Activating Token Index: 545

Text #17

Max Range: 1.3708. Min Range: -1.3708

Max Act: 0.9962. Min Act: -0.0000

Data Index: 1846472 (The Pile)

Max Activating Token Index: 613

Text #18

Max Range: 1.3708. Min Range: -1.3708

Max Act: 0.9914. Min Act: -0.0000

Data Index: 772962 (The Pile)

Max Activating Token Index: 490

Text #19

Max Range: 1.3708. Min Range: -1.3708

Max Act: 0.9927. Min Act: -0.0000

Data Index: 1358774 (The Pile)

Max Activating Token Index: 833