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

Dataset: The Pile

Neuron 2709 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.7608. Min Act: -0.0000

Data Index: 830980 (The Pile)

Max Activating Token Index: 760

Text #1

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.6876. Min Act: -0.0000

Data Index: 1130596 (The Pile)

Max Activating Token Index: 167

Text #2

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.7638. Min Act: -0.0000

Data Index: 1263841 (The Pile)

Max Activating Token Index: 784

Text #3

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.6994. Min Act: -0.0000

Data Index: 875779 (The Pile)

Max Activating Token Index: 739

Text #4

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.6354. Min Act: -0.0000

Data Index: 79308 (The Pile)

Max Activating Token Index: 1022

Text #5

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.6666. Min Act: -0.0000

Data Index: 483618 (The Pile)

Max Activating Token Index: 508

Text #6

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.6622. Min Act: -0.0000

Data Index: 814822 (The Pile)

Max Activating Token Index: 680

Text #7

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.6039. Min Act: -0.0000

Data Index: 509495 (The Pile)

Max Activating Token Index: 389

Text #8

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.6417. Min Act: -0.0000

Data Index: 716004 (The Pile)

Max Activating Token Index: 122

Text #9

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.6600. Min Act: -0.0000

Data Index: 1197769 (The Pile)

Max Activating Token Index: 701

Text #10

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.5550. Min Act: -0.0000

Data Index: 1761218 (The Pile)

Max Activating Token Index: 712

Text #11

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.5788. Min Act: -0.0000

Data Index: 1819008 (The Pile)

Max Activating Token Index: 276

Text #12

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.6587. Min Act: -0.0000

Data Index: 1760047 (The Pile)

Max Activating Token Index: 91

Text #13

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.6280. Min Act: -0.0000

Data Index: 982961 (The Pile)

Max Activating Token Index: 649

Text #14

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.6030. Min Act: -0.0000

Data Index: 570698 (The Pile)

Max Activating Token Index: 896

Text #15

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.5789. Min Act: -0.0000

Data Index: 1096343 (The Pile)

Max Activating Token Index: 153

Text #16

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.5841. Min Act: -0.0000

Data Index: 207942 (The Pile)

Max Activating Token Index: 38

Text #17

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.6264. Min Act: -0.0000

Data Index: 311339 (The Pile)

Max Activating Token Index: 667

Text #18

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.6116. Min Act: -0.0000

Data Index: 1490209 (The Pile)

Max Activating Token Index: 434

Text #19

Max Range: 0.7638. Min Range: -0.7638

Max Act: 0.5502. Min Act: -0.0000

Data Index: 1209376 (The Pile)

Max Activating Token Index: 610