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

Dataset: The Pile

Neuron 906 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: 1.8670. Min Range: -1.8670

Max Act: 1.8670. Min Act: -0.0000

Data Index: 1807167 (The Pile)

Max Activating Token Index: 231

Text #1

Max Range: 1.8670. Min Range: -1.8670

Max Act: 1.3713. Min Act: -0.0000

Data Index: 489347 (The Pile)

Max Activating Token Index: 951

Text #2

Max Range: 1.8670. Min Range: -1.8670

Max Act: 1.1937. Min Act: -0.0000

Data Index: 331679 (The Pile)

Max Activating Token Index: 388

Text #3

Max Range: 1.8670. Min Range: -1.8670

Max Act: 1.2765. Min Act: -0.0000

Data Index: 1623873 (The Pile)

Max Activating Token Index: 936

Text #4

Max Range: 1.8670. Min Range: -1.8670

Max Act: 1.1560. Min Act: -0.0000

Data Index: 1948732 (The Pile)

Max Activating Token Index: 610

Text #5

Max Range: 1.8670. Min Range: -1.8670

Max Act: 1.1761. Min Act: -0.0000

Data Index: 709589 (The Pile)

Max Activating Token Index: 322

Text #6

Max Range: 1.8670. Min Range: -1.8670

Max Act: 1.2877. Min Act: 0.0000

Data Index: 640277 (The Pile)

Max Activating Token Index: 171

Text #7

Max Range: 1.8670. Min Range: -1.8670

Max Act: 1.0893. Min Act: -0.0000

Data Index: 35786 (The Pile)

Max Activating Token Index: 749

Text #8

Max Range: 1.8670. Min Range: -1.8670

Max Act: 1.1059. Min Act: -0.0000

Data Index: 1760680 (The Pile)

Max Activating Token Index: 907

Text #9

Max Range: 1.8670. Min Range: -1.8670

Max Act: 1.1296. Min Act: -0.0000

Data Index: 1781110 (The Pile)

Max Activating Token Index: 108

Text #10

Max Range: 1.8670. Min Range: -1.8670

Max Act: 1.1038. Min Act: -0.0000

Data Index: 161985 (The Pile)

Max Activating Token Index: 762

Text #11

Max Range: 1.8670. Min Range: -1.8670

Max Act: 1.0377. Min Act: -0.0000

Data Index: 1226075 (The Pile)

Max Activating Token Index: 780

Text #12

Max Range: 1.8670. Min Range: -1.8670

Max Act: 1.1034. Min Act: -0.0000

Data Index: 1390849 (The Pile)

Max Activating Token Index: 607

Text #13

Max Range: 1.8670. Min Range: -1.8670

Max Act: 1.0946. Min Act: -0.0000

Data Index: 412074 (The Pile)

Max Activating Token Index: 258

Text #14

Max Range: 1.8670. Min Range: -1.8670

Max Act: 1.0204. Min Act: -0.0000

Data Index: 1812188 (The Pile)

Max Activating Token Index: 383

Text #15

Max Range: 1.8670. Min Range: -1.8670

Max Act: 1.0738. Min Act: -0.0000

Data Index: 87179 (The Pile)

Max Activating Token Index: 863

Text #16

Max Range: 1.8670. Min Range: -1.8670

Max Act: 1.1497. Min Act: -0.0000

Data Index: 1423649 (The Pile)

Max Activating Token Index: 446

Text #17

Max Range: 1.8670. Min Range: -1.8670

Max Act: 1.1306. Min Act: -0.0000

Data Index: 681863 (The Pile)

Max Activating Token Index: 521

Text #18

Max Range: 1.8670. Min Range: -1.8670

Max Act: 1.0825. Min Act: -0.0000

Data Index: 1293741 (The Pile)

Max Activating Token Index: 461

Text #19

Max Range: 1.8670. Min Range: -1.8670

Max Act: 1.0733. Min Act: -0.0000

Data Index: 419720 (The Pile)

Max Activating Token Index: 442