Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 324 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.1186. Min Act: -0.0003

Data Index: 370271 (C4 (Web Text))

Max Activating Token Index: 365

Text #1

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0923. Min Act: -0.0003

Data Index: 780262 (C4 (Web Text))

Max Activating Token Index: 408

Text #2

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0886. Min Act: -0.0003

Data Index: 532106 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0813. Min Act: -0.0003

Data Index: 150499 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0884. Min Act: -0.0003

Data Index: 1057529 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0834. Min Act: -0.0003

Data Index: 1241805 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0818. Min Act: -0.0003

Data Index: 926962 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0676. Min Act: -0.0003

Data Index: 669639 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0806. Min Act: -0.0003

Data Index: 49086 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0805. Min Act: -0.0003

Data Index: 601484 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0885. Min Act: -0.0003

Data Index: 80734 (C4 (Web Text))

Max Activating Token Index: 271

Text #11

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0823. Min Act: -0.0003

Data Index: 686831 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0756. Min Act: -0.0003

Data Index: 596938 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0815. Min Act: -0.0003

Data Index: 255184 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0776. Min Act: -0.0003

Data Index: 1122441 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0785. Min Act: -0.0003

Data Index: 118709 (C4 (Web Text))

Max Activating Token Index: 194

Text #16

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0777. Min Act: -0.0003

Data Index: 1201430 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0804. Min Act: -0.0003

Data Index: 266592 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0806. Min Act: -0.0003

Data Index: 204790 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0775. Min Act: -0.0003

Data Index: 1068514 (C4 (Web Text))

Max Activating Token Index: 748