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

Dataset: The Pile

Neuron 2581 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4435. Min Range: -1.4435

Max Act: 1.3877. Min Act: -0.0000

Data Index: 1694980 (The Pile)

Max Activating Token Index: 109

Text #1

Max Range: 1.4435. Min Range: -1.4435

Max Act: 1.4435. Min Act: -0.0000

Data Index: 43753 (The Pile)

Max Activating Token Index: 642

Text #2

Max Range: 1.4435. Min Range: -1.4435

Max Act: 1.3634. Min Act: -0.0000

Data Index: 1603844 (The Pile)

Max Activating Token Index: 964

Text #3

Max Range: 1.4435. Min Range: -1.4435

Max Act: 1.3292. Min Act: -0.0000

Data Index: 1160716 (The Pile)

Max Activating Token Index: 310

Text #4

Max Range: 1.4435. Min Range: -1.4435

Max Act: 1.2522. Min Act: -0.0000

Data Index: 1095484 (The Pile)

Max Activating Token Index: 346

Text #5

Max Range: 1.4435. Min Range: -1.4435

Max Act: 1.2931. Min Act: -0.0000

Data Index: 1783904 (The Pile)

Max Activating Token Index: 42

Text #6

Max Range: 1.4435. Min Range: -1.4435

Max Act: 1.1931. Min Act: -0.0000

Data Index: 1015618 (The Pile)

Max Activating Token Index: 232

Text #7

Max Range: 1.4435. Min Range: -1.4435

Max Act: 1.2444. Min Act: -0.0000

Data Index: 1695879 (The Pile)

Max Activating Token Index: 618

Text #8

Max Range: 1.4435. Min Range: -1.4435

Max Act: 1.1133. Min Act: -0.0000

Data Index: 1918269 (The Pile)

Max Activating Token Index: 315

Text #9

Max Range: 1.4435. Min Range: -1.4435

Max Act: 1.1829. Min Act: -0.0000

Data Index: 1742934 (The Pile)

Max Activating Token Index: 11

Text #10

Max Range: 1.4435. Min Range: -1.4435

Max Act: 1.1677. Min Act: -0.0000

Data Index: 706153 (The Pile)

Max Activating Token Index: 671

Text #11

Max Range: 1.4435. Min Range: -1.4435

Max Act: 1.1692. Min Act: -0.0000

Data Index: 199992 (The Pile)

Max Activating Token Index: 869

Text #12

Max Range: 1.4435. Min Range: -1.4435

Max Act: 1.1257. Min Act: -0.0000

Data Index: 181181 (The Pile)

Max Activating Token Index: 491

Text #13

Max Range: 1.4435. Min Range: -1.4435

Max Act: 1.1148. Min Act: -0.0000

Data Index: 212794 (The Pile)

Max Activating Token Index: 483

Text #14

Max Range: 1.4435. Min Range: -1.4435

Max Act: 1.0972. Min Act: -0.0000

Data Index: 402771 (The Pile)

Max Activating Token Index: 908

Text #15

Max Range: 1.4435. Min Range: -1.4435

Max Act: 1.0999. Min Act: -0.0000

Data Index: 253750 (The Pile)

Max Activating Token Index: 72

Text #16

Max Range: 1.4435. Min Range: -1.4435

Max Act: 1.0250. Min Act: -0.0000

Data Index: 1519933 (The Pile)

Max Activating Token Index: 29

Text #17

Max Range: 1.4435. Min Range: -1.4435

Max Act: 1.0813. Min Act: -0.0000

Data Index: 454722 (The Pile)

Max Activating Token Index: 681

Text #18

Max Range: 1.4435. Min Range: -1.4435

Max Act: 1.0826. Min Act: -0.0000

Data Index: 921275 (The Pile)

Max Activating Token Index: 241

Text #19

Max Range: 1.4435. Min Range: -1.4435

Max Act: 1.0669. Min Act: -0.0000

Data Index: 417671 (The Pile)

Max Activating Token Index: 756