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

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

Neuron 3394 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: 0.1093. Min Range: -0.1093

Max Act: 0.1093. Min Act: -0.0002

Data Index: 966575 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.1069. Min Act: -0.0002

Data Index: 297244 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0937. Min Act: -0.0002

Data Index: 206677 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0962. Min Act: -0.0002

Data Index: 1283905 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0929. Min Act: -0.0002

Data Index: 695876 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0910. Min Act: -0.0002

Data Index: 1296078 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0903. Min Act: -0.0002

Data Index: 583978 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0880. Min Act: -0.0002

Data Index: 931557 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0873. Min Act: -0.0002

Data Index: 609443 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0815. Min Act: -0.0002

Data Index: 1348302 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0856. Min Act: -0.0002

Data Index: 296850 (C4 (Web Text))

Max Activating Token Index: 153

Text #11

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0859. Min Act: -0.0002

Data Index: 564698 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0877. Min Act: -0.0002

Data Index: 123542 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0798. Min Act: -0.0002

Data Index: 4254 (C4 (Web Text))

Max Activating Token Index: 336

Text #14

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0773. Min Act: -0.0002

Data Index: 1338947 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0800. Min Act: -0.0002

Data Index: 484039 (C4 (Web Text))

Max Activating Token Index: 269

Text #16

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0805. Min Act: -0.0002

Data Index: 79854 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0833. Min Act: -0.0002

Data Index: 1176494 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0830. Min Act: -0.0002

Data Index: 247636 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0781. Min Act: -0.0002

Data Index: 554264 (C4 (Web Text))

Max Activating Token Index: 207