Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3702 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.5885. Min Act: -0.0000

Data Index: 42041 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.6269. Min Act: -0.0000

Data Index: 999574 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.5845. Min Act: -0.0000

Data Index: 859019 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.5396. Min Act: -0.0000

Data Index: 257811 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.4446. Min Act: -0.0000

Data Index: 1090115 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.5221. Min Act: -0.0000

Data Index: 1288832 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.5094. Min Act: -0.0000

Data Index: 1185481 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.5040. Min Act: -0.0000

Data Index: 923248 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.4961. Min Act: -0.0000

Data Index: 1268655 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.4510. Min Act: -0.0000

Data Index: 965089 (C4 (Web Text))

Max Activating Token Index: 94

Text #10

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.4330. Min Act: -0.0000

Data Index: 444504 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.5275. Min Act: -0.0000

Data Index: 161634 (C4 (Web Text))

Max Activating Token Index: 235

Text #12

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.4316. Min Act: -0.0000

Data Index: 1165082 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.4137. Min Act: -0.0000

Data Index: 724301 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.4032. Min Act: -0.0000

Data Index: 801391 (C4 (Web Text))

Max Activating Token Index: 567

Text #15

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.4024. Min Act: -0.0000

Data Index: 1109760 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.4055. Min Act: -0.0000

Data Index: 304113 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.3970. Min Act: -0.0000

Data Index: 1339729 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.4812. Min Act: -0.0000

Data Index: 820802 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.2876. Min Act: -0.0000

Data Index: 1108487 (C4 (Web Text))

Max Activating Token Index: 378