Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 752 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.7825. Min Range: -5.7825

Max Act: 5.7825. Min Act: -0.0001

Data Index: 152527 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 5.7825. Min Range: -5.7825

Max Act: 5.2092. Min Act: -0.0000

Data Index: 528505 (C4 (Web Text))

Max Activating Token Index: 696

Text #2

Max Range: 5.7825. Min Range: -5.7825

Max Act: 5.0516. Min Act: -0.0000

Data Index: 1083678 (C4 (Web Text))

Max Activating Token Index: 254

Text #3

Max Range: 5.7825. Min Range: -5.7825

Max Act: 4.7215. Min Act: -0.0001

Data Index: 958635 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 5.7825. Min Range: -5.7825

Max Act: 4.6031. Min Act: -0.0001

Data Index: 425769 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 5.7825. Min Range: -5.7825

Max Act: 4.1717. Min Act: -0.0000

Data Index: 817249 (C4 (Web Text))

Max Activating Token Index: 504

Text #6

Max Range: 5.7825. Min Range: -5.7825

Max Act: 3.6928. Min Act: -0.0001

Data Index: 675188 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 5.7825. Min Range: -5.7825

Max Act: 3.1934. Min Act: -0.0000

Data Index: 1125797 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 5.7825. Min Range: -5.7825

Max Act: 3.0863. Min Act: -0.0000

Data Index: 933869 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 5.7825. Min Range: -5.7825

Max Act: 2.7056. Min Act: -0.0000

Data Index: 1293802 (C4 (Web Text))

Max Activating Token Index: 835

Text #10

Max Range: 5.7825. Min Range: -5.7825

Max Act: 2.9428. Min Act: -0.0000

Data Index: 1214807 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 5.7825. Min Range: -5.7825

Max Act: 2.9193. Min Act: -0.0000

Data Index: 611146 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 5.7825. Min Range: -5.7825

Max Act: 2.9904. Min Act: -0.0000

Data Index: 1074618 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 5.7825. Min Range: -5.7825

Max Act: 2.7547. Min Act: -0.0001

Data Index: 940406 (C4 (Web Text))

Max Activating Token Index: 733

Text #14

Max Range: 5.7825. Min Range: -5.7825

Max Act: 2.7267. Min Act: -0.0000

Data Index: 856361 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 5.7825. Min Range: -5.7825

Max Act: 2.7025. Min Act: -0.0000

Data Index: 870727 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 5.7825. Min Range: -5.7825

Max Act: 2.7917. Min Act: -0.0000

Data Index: 506007 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 5.7825. Min Range: -5.7825

Max Act: 2.7805. Min Act: -0.0000

Data Index: 1183148 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 5.7825. Min Range: -5.7825

Max Act: 2.8379. Min Act: -0.0000

Data Index: 1241110 (C4 (Web Text))

Max Activating Token Index: 723

Text #19

Max Range: 5.7825. Min Range: -5.7825

Max Act: 2.6841. Min Act: -0.0000

Data Index: 1018861 (C4 (Web Text))

Max Activating Token Index: 275