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

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

Neuron 4804 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.4884. Min Act: -0.0000

Data Index: 945164 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.3196. Min Act: -0.0000

Data Index: 239589 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.3641. Min Act: -0.0000

Data Index: 852391 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.3264. Min Act: -0.0000

Data Index: 991774 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.2864. Min Act: -0.0000

Data Index: 721202 (C4 (Web Text))

Max Activating Token Index: 828

Text #5

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.1805. Min Act: -0.0000

Data Index: 668708 (C4 (Web Text))

Max Activating Token Index: 177

Text #6

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.2582. Min Act: -0.0000

Data Index: 668586 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.2044. Min Act: -0.0000

Data Index: 1020774 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.2073. Min Act: -0.0000

Data Index: 1349243 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.1874. Min Act: -0.0000

Data Index: 472126 (C4 (Web Text))

Max Activating Token Index: 851

Text #10

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.1770. Min Act: -0.0000

Data Index: 728634 (C4 (Web Text))

Max Activating Token Index: 437

Text #11

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.1121. Min Act: -0.0000

Data Index: 544932 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.1678. Min Act: -0.0000

Data Index: 330602 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.1605. Min Act: -0.0000

Data Index: 1172104 (C4 (Web Text))

Max Activating Token Index: 348

Text #14

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.0283. Min Act: -0.0000

Data Index: 656581 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.0759. Min Act: -0.0000

Data Index: 971586 (C4 (Web Text))

Max Activating Token Index: 754

Text #16

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.1444. Min Act: -0.0000

Data Index: 1264714 (C4 (Web Text))

Max Activating Token Index: 360

Text #17

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.1093. Min Act: -0.0000

Data Index: 619733 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.1949. Min Act: -0.0000

Data Index: 1354943 (C4 (Web Text))

Max Activating Token Index: 708

Text #19

Max Range: 1.4884. Min Range: -1.4884

Max Act: 1.1591. Min Act: -0.0000

Data Index: 716352 (C4 (Web Text))

Max Activating Token Index: 269