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

Dataset: The Pile

Neuron 1329 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.6783. Min Act: -0.0000

Data Index: 1017890 (The Pile)

Max Activating Token Index: 464

Text #1

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.5424. Min Act: -0.0000

Data Index: 1576989 (The Pile)

Max Activating Token Index: 777

Text #2

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.6125. Min Act: -0.0000

Data Index: 452117 (The Pile)

Max Activating Token Index: 344

Text #3

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.5580. Min Act: -0.0000

Data Index: 1813458 (The Pile)

Max Activating Token Index: 23

Text #4

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.4549. Min Act: -0.0000

Data Index: 1314595 (The Pile)

Max Activating Token Index: 314

Text #5

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.5347. Min Act: -0.0000

Data Index: 775747 (The Pile)

Max Activating Token Index: 221

Text #6

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.4287. Min Act: -0.0000

Data Index: 1814654 (The Pile)

Max Activating Token Index: 893

Text #7

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.4561. Min Act: -0.0000

Data Index: 657370 (The Pile)

Max Activating Token Index: 495

Text #8

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.3881. Min Act: -0.0000

Data Index: 1399776 (The Pile)

Max Activating Token Index: 61

Text #9

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.3868. Min Act: -0.0000

Data Index: 145436 (The Pile)

Max Activating Token Index: 25

Text #10

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.3719. Min Act: -0.0000

Data Index: 78974 (The Pile)

Max Activating Token Index: 643

Text #11

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.3805. Min Act: -0.0000

Data Index: 86967 (The Pile)

Max Activating Token Index: 247

Text #12

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.3807. Min Act: -0.0000

Data Index: 442175 (The Pile)

Max Activating Token Index: 567

Text #13

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.4469. Min Act: -0.0000

Data Index: 1146141 (The Pile)

Max Activating Token Index: 341

Text #14

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.2890. Min Act: -0.0000

Data Index: 580649 (The Pile)

Max Activating Token Index: 409

Text #15

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.3569. Min Act: -0.0000

Data Index: 388250 (The Pile)

Max Activating Token Index: 877

Text #16

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.3211. Min Act: -0.0000

Data Index: 1630349 (The Pile)

Max Activating Token Index: 456

Text #17

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.2758. Min Act: -0.0000

Data Index: 1508730 (The Pile)

Max Activating Token Index: 131

Text #18

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.1896. Min Act: -0.0000

Data Index: 862411 (The Pile)

Max Activating Token Index: 701

Text #19

Max Range: 1.6783. Min Range: -1.6783

Max Act: 1.3207. Min Act: -0.0000

Data Index: 613666 (The Pile)

Max Activating Token Index: 1021