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

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

Neuron 40 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: 1.8616. Min Range: -1.8616

Max Act: 1.8616. Min Act: -0.0000

Data Index: 13692 (C4 (Web Text))

Max Activating Token Index: 202

Text #1

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.7721. Min Act: -0.0000

Data Index: 782861 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.7388. Min Act: -0.0000

Data Index: 1164882 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.7022. Min Act: -0.0000

Data Index: 527296 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.5570. Min Act: -0.0000

Data Index: 842857 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.6578. Min Act: -0.0000

Data Index: 1072888 (C4 (Web Text))

Max Activating Token Index: 481

Text #6

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.7228. Min Act: -0.0000

Data Index: 1232576 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.5920. Min Act: -0.0000

Data Index: 796849 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.4991. Min Act: -0.0000

Data Index: 535106 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.5402. Min Act: -0.0000

Data Index: 1213798 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.5230. Min Act: -0.0000

Data Index: 103852 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.5051. Min Act: -0.0000

Data Index: 1324459 (C4 (Web Text))

Max Activating Token Index: 632

Text #12

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.4583. Min Act: -0.0000

Data Index: 325536 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.5711. Min Act: -0.0000

Data Index: 892955 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.4627. Min Act: -0.0000

Data Index: 221788 (C4 (Web Text))

Max Activating Token Index: 494

Text #15

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.3435. Min Act: -0.0000

Data Index: 187527 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.6009. Min Act: -0.0000

Data Index: 489158 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.3662. Min Act: -0.0000

Data Index: 1288123 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.4487. Min Act: -0.0000

Data Index: 1060147 (C4 (Web Text))

Max Activating Token Index: 245

Text #19

Max Range: 1.8616. Min Range: -1.8616

Max Act: 1.4582. Min Act: -0.0000

Data Index: 766225 (C4 (Web Text))

Max Activating Token Index: 513