Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3687 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1622. Min Act: -0.0003

Data Index: 99872 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1149. Min Act: -0.0003

Data Index: 548216 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.1025. Min Act: -0.0003

Data Index: 937689 (C4 (Web Text))

Max Activating Token Index: 661

Text #3

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.0945. Min Act: -0.0003

Data Index: 1115620 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.0980. Min Act: -0.0003

Data Index: 180828 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.0941. Min Act: -0.0003

Data Index: 920546 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.0887. Min Act: -0.0003

Data Index: 672812 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.0884. Min Act: -0.0003

Data Index: 1217572 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.0878. Min Act: -0.0002

Data Index: 289627 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.0862. Min Act: -0.0003

Data Index: 479726 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.0852. Min Act: -0.0002

Data Index: 78869 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.0844. Min Act: -0.0002

Data Index: 1176879 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.0836. Min Act: -0.0002

Data Index: 503785 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.0836. Min Act: -0.0003

Data Index: 1048898 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.0793. Min Act: -0.0002

Data Index: 140767 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.0822. Min Act: -0.0003

Data Index: 768875 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.0787. Min Act: -0.0003

Data Index: 732309 (C4 (Web Text))

Max Activating Token Index: 782

Text #17

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.0817. Min Act: -0.0003

Data Index: 651570 (C4 (Web Text))

Max Activating Token Index: 719

Text #18

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.0810. Min Act: -0.0003

Data Index: 656316 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 0.1622. Min Range: -0.1622

Max Act: 0.0807. Min Act: -0.0002

Data Index: 946501 (C4 (Web Text))

Max Activating Token Index: 418