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

Dataset: The Pile

Neuron 44 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.1782. Min Act: -0.0000

Data Index: 669823 (The Pile)

Max Activating Token Index: 340

Text #1

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.9204. Min Act: -0.0000

Data Index: 1229859 (The Pile)

Max Activating Token Index: 796

Text #2

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.9771. Min Act: -0.0000

Data Index: 1263322 (The Pile)

Max Activating Token Index: 864

Text #3

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.9094. Min Act: -0.0000

Data Index: 965385 (The Pile)

Max Activating Token Index: 660

Text #4

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.9133. Min Act: -0.0000

Data Index: 803680 (The Pile)

Max Activating Token Index: 869

Text #5

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.8645. Min Act: -0.0000

Data Index: 1958702 (The Pile)

Max Activating Token Index: 231

Text #6

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.8113. Min Act: -0.0000

Data Index: 1413751 (The Pile)

Max Activating Token Index: 30

Text #7

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.7872. Min Act: -0.0000

Data Index: 480650 (The Pile)

Max Activating Token Index: 132

Text #8

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.8113. Min Act: -0.0000

Data Index: 87335 (The Pile)

Max Activating Token Index: 321

Text #9

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.7704. Min Act: -0.0000

Data Index: 408160 (The Pile)

Max Activating Token Index: 728

Text #10

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.8200. Min Act: -0.0000

Data Index: 1661923 (The Pile)

Max Activating Token Index: 250

Text #11

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.7459. Min Act: -0.0000

Data Index: 1530261 (The Pile)

Max Activating Token Index: 127

Text #12

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.8033. Min Act: -0.0000

Data Index: 1801265 (The Pile)

Max Activating Token Index: 621

Text #13

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.7516. Min Act: -0.0000

Data Index: 815769 (The Pile)

Max Activating Token Index: 657

Text #14

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.7797. Min Act: -0.0000

Data Index: 1600775 (The Pile)

Max Activating Token Index: 891

Text #15

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.7485. Min Act: -0.0000

Data Index: 1534030 (The Pile)

Max Activating Token Index: 609

Text #16

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.7034. Min Act: -0.0000

Data Index: 1564109 (The Pile)

Max Activating Token Index: 207

Text #17

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.7520. Min Act: -0.0000

Data Index: 74403 (The Pile)

Max Activating Token Index: 783

Text #18

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.6965. Min Act: -0.0000

Data Index: 1329766 (The Pile)

Max Activating Token Index: 763

Text #19

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.7776. Min Act: -0.0000

Data Index: 1912790 (The Pile)

Max Activating Token Index: 226