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

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

Neuron 4383 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: 0.1071. Min Range: -0.1071

Max Act: 0.1050. Min Act: -0.0002

Data Index: 629243 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.1071. Min Act: -0.0002

Data Index: 968014 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.1024. Min Act: -0.0002

Data Index: 732950 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0942. Min Act: -0.0002

Data Index: 458259 (C4 (Web Text))

Max Activating Token Index: 735

Text #4

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0995. Min Act: -0.0002

Data Index: 1284972 (C4 (Web Text))

Max Activating Token Index: 504

Text #5

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0983. Min Act: -0.0002

Data Index: 579246 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0880. Min Act: -0.0002

Data Index: 682623 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0925. Min Act: -0.0002

Data Index: 191083 (C4 (Web Text))

Max Activating Token Index: 651

Text #8

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0821. Min Act: -0.0002

Data Index: 320079 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0908. Min Act: -0.0002

Data Index: 602946 (C4 (Web Text))

Max Activating Token Index: 474

Text #10

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0876. Min Act: -0.0002

Data Index: 1056153 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0864. Min Act: -0.0002

Data Index: 337418 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0867. Min Act: -0.0002

Data Index: 498259 (C4 (Web Text))

Max Activating Token Index: 369

Text #13

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0768. Min Act: -0.0002

Data Index: 984451 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0778. Min Act: -0.0002

Data Index: 218420 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0729. Min Act: -0.0002

Data Index: 1298509 (C4 (Web Text))

Max Activating Token Index: 984

Text #16

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0781. Min Act: -0.0002

Data Index: 659403 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0754. Min Act: -0.0002

Data Index: 351031 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0772. Min Act: -0.0002

Data Index: 482897 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0743. Min Act: -0.0002

Data Index: 1280224 (C4 (Web Text))

Max Activating Token Index: 392