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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1090 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.2057. Min Act: -0.0001

Data Index: 600903 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.2001. Min Act: -0.0001

Data Index: 90291 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1993. Min Act: -0.0001

Data Index: 389822 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1916. Min Act: -0.0001

Data Index: 912599 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1963. Min Act: -0.0001

Data Index: 698367 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1905. Min Act: -0.0001

Data Index: 1006071 (C4 (Web Text))

Max Activating Token Index: 503

Text #6

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1788. Min Act: -0.0001

Data Index: 884587 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1789. Min Act: -0.0001

Data Index: 781327 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1711. Min Act: -0.0001

Data Index: 295469 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1761. Min Act: -0.0001

Data Index: 218576 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1932. Min Act: -0.0001

Data Index: 1035690 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1828. Min Act: -0.0001

Data Index: 334152 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1566. Min Act: -0.0001

Data Index: 601648 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1919. Min Act: -0.0001

Data Index: 165970 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1620. Min Act: -0.0001

Data Index: 1186661 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1713. Min Act: -0.0001

Data Index: 420285 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1755. Min Act: -0.0001

Data Index: 1207435 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1634. Min Act: -0.0001

Data Index: 116809 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1589. Min Act: -0.0001

Data Index: 1151293 (C4 (Web Text))

Max Activating Token Index: 765

Text #19

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1686. Min Act: -0.0001

Data Index: 813659 (C4 (Web Text))

Max Activating Token Index: 26