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

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

Neuron 1797 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.3439. Min Act: -0.0002

Data Index: 674894 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.3314. Min Act: -0.0002

Data Index: 714320 (C4 (Web Text))

Max Activating Token Index: 768

Text #2

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.3216. Min Act: -0.0002

Data Index: 965654 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.3068. Min Act: -0.0002

Data Index: 582257 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.3166. Min Act: -0.0002

Data Index: 1327902 (C4 (Web Text))

Max Activating Token Index: 417

Text #5

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.3130. Min Act: -0.0002

Data Index: 1195013 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.3014. Min Act: -0.0002

Data Index: 1276730 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.3001. Min Act: -0.0002

Data Index: 1246392 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2998. Min Act: -0.0002

Data Index: 1215924 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.3023. Min Act: -0.0002

Data Index: 1090291 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2896. Min Act: -0.0002

Data Index: 242736 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2873. Min Act: -0.0002

Data Index: 289809 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2867. Min Act: -0.0002

Data Index: 890445 (C4 (Web Text))

Max Activating Token Index: 379

Text #13

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2854. Min Act: -0.0002

Data Index: 420597 (C4 (Web Text))

Max Activating Token Index: 1002

Text #14

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2840. Min Act: -0.0002

Data Index: 450125 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2835. Min Act: -0.0002

Data Index: 551635 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2816. Min Act: -0.0002

Data Index: 1015544 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2797. Min Act: -0.0002

Data Index: 35719 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2780. Min Act: -0.0002

Data Index: 32059 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2779. Min Act: -0.0002

Data Index: 1347745 (C4 (Web Text))

Max Activating Token Index: 861