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

Dataset: The Pile

Neuron 3429 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: 0.6587. Min Range: -0.6587

Max Act: 0.6587. Min Act: -0.0000

Data Index: 716252 (The Pile)

Max Activating Token Index: 852

Text #1

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.6247. Min Act: -0.0000

Data Index: 568926 (The Pile)

Max Activating Token Index: 682

Text #2

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.5814. Min Act: -0.0000

Data Index: 1931214 (The Pile)

Max Activating Token Index: 664

Text #3

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.4677. Min Act: -0.0000

Data Index: 1299084 (The Pile)

Max Activating Token Index: 723

Text #4

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.4824. Min Act: -0.0000

Data Index: 375617 (The Pile)

Max Activating Token Index: 963

Text #5

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.4657. Min Act: -0.0000

Data Index: 766576 (The Pile)

Max Activating Token Index: 83

Text #6

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.4346. Min Act: -0.0000

Data Index: 1361317 (The Pile)

Max Activating Token Index: 354

Text #7

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.4500. Min Act: -0.0000

Data Index: 1098956 (The Pile)

Max Activating Token Index: 322

Text #8

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.4665. Min Act: -0.0000

Data Index: 574270 (The Pile)

Max Activating Token Index: 14

Text #9

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.4027. Min Act: -0.0000

Data Index: 38798 (The Pile)

Max Activating Token Index: 820

Text #10

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.4378. Min Act: -0.0000

Data Index: 239121 (The Pile)

Max Activating Token Index: 140

Text #11

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.4048. Min Act: -0.0000

Data Index: 880850 (The Pile)

Max Activating Token Index: 240

Text #12

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.4534. Min Act: -0.0000

Data Index: 511839 (The Pile)

Max Activating Token Index: 953

Text #13

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.3770. Min Act: -0.0000

Data Index: 1425829 (The Pile)

Max Activating Token Index: 842

Text #14

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.4171. Min Act: -0.0000

Data Index: 1797615 (The Pile)

Max Activating Token Index: 327

Text #15

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.3962. Min Act: -0.0000

Data Index: 1278618 (The Pile)

Max Activating Token Index: 318

Text #16

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.3873. Min Act: -0.0000

Data Index: 559215 (The Pile)

Max Activating Token Index: 714

Text #17

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.3935. Min Act: -0.0000

Data Index: 1738956 (The Pile)

Max Activating Token Index: 332

Text #18

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.3857. Min Act: -0.0000

Data Index: 1254554 (The Pile)

Max Activating Token Index: 660

Text #19

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.3536. Min Act: -0.0000

Data Index: 1956866 (The Pile)

Max Activating Token Index: 306