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

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

Neuron 3353 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: 0.7171. Min Range: -0.7171

Max Act: 0.6971. Min Act: -0.0001

Data Index: 689850 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 0.7171. Min Range: -0.7171

Max Act: 0.6630. Min Act: -0.0001

Data Index: 315617 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 0.7171. Min Range: -0.7171

Max Act: 0.7171. Min Act: -0.0001

Data Index: 207426 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 0.7171. Min Range: -0.7171

Max Act: 0.6361. Min Act: -0.0001

Data Index: 958194 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 0.7171. Min Range: -0.7171

Max Act: 0.6427. Min Act: -0.0001

Data Index: 1330466 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 0.7171. Min Range: -0.7171

Max Act: 0.6841. Min Act: -0.0001

Data Index: 828912 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 0.7171. Min Range: -0.7171

Max Act: 0.5884. Min Act: -0.0001

Data Index: 506543 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 0.7171. Min Range: -0.7171

Max Act: 0.6083. Min Act: -0.0001

Data Index: 1036914 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 0.7171. Min Range: -0.7171

Max Act: 0.5232. Min Act: -0.0001

Data Index: 186177 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 0.7171. Min Range: -0.7171

Max Act: 0.5532. Min Act: -0.0001

Data Index: 623003 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 0.7171. Min Range: -0.7171

Max Act: 0.4883. Min Act: -0.0001

Data Index: 1318647 (C4 (Web Text))

Max Activating Token Index: 919

Text #11

Max Range: 0.7171. Min Range: -0.7171

Max Act: 0.4662. Min Act: -0.0001

Data Index: 326850 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 0.7171. Min Range: -0.7171

Max Act: 0.4759. Min Act: -0.0001

Data Index: 539621 (C4 (Web Text))

Max Activating Token Index: 612

Text #13

Max Range: 0.7171. Min Range: -0.7171

Max Act: 0.5092. Min Act: -0.0001

Data Index: 567978 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 0.7171. Min Range: -0.7171

Max Act: 0.5017. Min Act: -0.0001

Data Index: 1339555 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 0.7171. Min Range: -0.7171

Max Act: 0.4565. Min Act: -0.0001

Data Index: 1047884 (C4 (Web Text))

Max Activating Token Index: 731

Text #16

Max Range: 0.7171. Min Range: -0.7171

Max Act: 0.5171. Min Act: -0.0001

Data Index: 891250 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 0.7171. Min Range: -0.7171

Max Act: 0.4875. Min Act: -0.0001

Data Index: 258867 (C4 (Web Text))

Max Activating Token Index: 2

Text #18

Max Range: 0.7171. Min Range: -0.7171

Max Act: 0.4875. Min Act: -0.0001

Data Index: 667024 (C4 (Web Text))

Max Activating Token Index: 2

Text #19

Max Range: 0.7171. Min Range: -0.7171

Max Act: 0.4886. Min Act: -0.0001

Data Index: 684775 (C4 (Web Text))

Max Activating Token Index: 27