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

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

Neuron 4367 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6704. Min Range: -0.6704

Max Act: 0.5271. Min Act: -0.0002

Data Index: 795387 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 0.6704. Min Range: -0.6704

Max Act: 0.6704. Min Act: -0.0002

Data Index: 1064172 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 0.6704. Min Range: -0.6704

Max Act: 0.5305. Min Act: -0.0002

Data Index: 860913 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 0.6704. Min Range: -0.6704

Max Act: 0.5294. Min Act: -0.0002

Data Index: 1085248 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 0.6704. Min Range: -0.6704

Max Act: 0.5990. Min Act: -0.0002

Data Index: 974833 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 0.6704. Min Range: -0.6704

Max Act: 0.6015. Min Act: -0.0002

Data Index: 190503 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 0.6704. Min Range: -0.6704

Max Act: 0.5212. Min Act: -0.0002

Data Index: 121556 (C4 (Web Text))

Max Activating Token Index: 479

Text #7

Max Range: 0.6704. Min Range: -0.6704

Max Act: 0.5513. Min Act: -0.0002

Data Index: 173031 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 0.6704. Min Range: -0.6704

Max Act: 0.5251. Min Act: -0.0002

Data Index: 1066151 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 0.6704. Min Range: -0.6704

Max Act: 0.5061. Min Act: -0.0002

Data Index: 659839 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 0.6704. Min Range: -0.6704

Max Act: 0.5245. Min Act: -0.0002

Data Index: 427610 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 0.6704. Min Range: -0.6704

Max Act: 0.4614. Min Act: -0.0002

Data Index: 1202334 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 0.6704. Min Range: -0.6704

Max Act: 0.4919. Min Act: -0.0002

Data Index: 1012735 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 0.6704. Min Range: -0.6704

Max Act: 0.4987. Min Act: -0.0002

Data Index: 686465 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 0.6704. Min Range: -0.6704

Max Act: 0.4844. Min Act: -0.0002

Data Index: 138255 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 0.6704. Min Range: -0.6704

Max Act: 0.5415. Min Act: -0.0002

Data Index: 1213507 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 0.6704. Min Range: -0.6704

Max Act: 0.4774. Min Act: -0.0002

Data Index: 803125 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 0.6704. Min Range: -0.6704

Max Act: 0.4351. Min Act: -0.0002

Data Index: 233055 (C4 (Web Text))

Max Activating Token Index: 773

Text #18

Max Range: 0.6704. Min Range: -0.6704

Max Act: 0.5052. Min Act: -0.0002

Data Index: 365995 (C4 (Web Text))

Max Activating Token Index: 529

Text #19

Max Range: 0.6704. Min Range: -0.6704

Max Act: 0.3771. Min Act: -0.0002

Data Index: 138220 (C4 (Web Text))

Max Activating Token Index: 275