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

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

Neuron 692 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.9672. Min Act: -0.0000

Data Index: 1100111 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.8293. Min Act: -0.0000

Data Index: 1038866 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.7793. Min Act: -0.0000

Data Index: 35914 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.7599. Min Act: -0.0000

Data Index: 894502 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.7488. Min Act: -0.0000

Data Index: 1060363 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.7511. Min Act: -0.0000

Data Index: 76530 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.7167. Min Act: -0.0000

Data Index: 17483 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.7027. Min Act: -0.0000

Data Index: 869664 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.7707. Min Act: -0.0000

Data Index: 475267 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.7005. Min Act: -0.0000

Data Index: 871504 (C4 (Web Text))

Max Activating Token Index: 442

Text #10

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.6345. Min Act: -0.0000

Data Index: 1270787 (C4 (Web Text))

Max Activating Token Index: 478

Text #11

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.6924. Min Act: -0.0000

Data Index: 952664 (C4 (Web Text))

Max Activating Token Index: 843

Text #12

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.6936. Min Act: -0.0000

Data Index: 505930 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.7028. Min Act: -0.0000

Data Index: 352304 (C4 (Web Text))

Max Activating Token Index: 244

Text #14

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.6721. Min Act: -0.0000

Data Index: 768047 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.6587. Min Act: -0.0000

Data Index: 134348 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.6280. Min Act: -0.0000

Data Index: 413847 (C4 (Web Text))

Max Activating Token Index: 9

Text #17

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.6682. Min Act: -0.0000

Data Index: 240057 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.6062. Min Act: -0.0000

Data Index: 306868 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 0.9672. Min Range: -0.9672

Max Act: 0.5977. Min Act: -0.0000

Data Index: 732951 (C4 (Web Text))

Max Activating Token Index: 869