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

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

Neuron 4811 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0258. Min Range: -1.0258

Max Act: 1.0258. Min Act: 0.0000

Data Index: 639867 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.9230. Min Act: -0.0000

Data Index: 752158 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.8575. Min Act: 0.0001

Data Index: 655275 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.7794. Min Act: -0.0000

Data Index: 1145985 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.7035. Min Act: -0.0000

Data Index: 846673 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.6563. Min Act: 0.0000

Data Index: 243370 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.7484. Min Act: 0.0000

Data Index: 1150296 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.6440. Min Act: 0.0000

Data Index: 194082 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.6584. Min Act: 0.0001

Data Index: 983049 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.6649. Min Act: -0.0000

Data Index: 1229505 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.6214. Min Act: 0.0000

Data Index: 759084 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.6759. Min Act: 0.0000

Data Index: 1250530 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.6569. Min Act: -0.0000

Data Index: 415052 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.6894. Min Act: -0.0000

Data Index: 71797 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.6501. Min Act: -0.0000

Data Index: 494837 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.5941. Min Act: -0.0000

Data Index: 208257 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.6198. Min Act: -0.0000

Data Index: 467933 (C4 (Web Text))

Max Activating Token Index: 244

Text #17

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.5858. Min Act: 0.0000

Data Index: 731619 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.6037. Min Act: 0.0000

Data Index: 801435 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 1.0258. Min Range: -1.0258

Max Act: 0.6061. Min Act: 0.0000

Data Index: 1215666 (C4 (Web Text))

Max Activating Token Index: 973