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

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

Neuron 3700 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.9570. Min Act: -0.0000

Data Index: 1135555 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.8324. Min Act: -0.0000

Data Index: 693482 (C4 (Web Text))

Max Activating Token Index: 639

Text #2

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.9692. Min Act: -0.0000

Data Index: 1008138 (C4 (Web Text))

Max Activating Token Index: 334

Text #3

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.8184. Min Act: -0.0000

Data Index: 689763 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.7916. Min Act: -0.0000

Data Index: 827561 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.7303. Min Act: -0.0000

Data Index: 188926 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.8234. Min Act: -0.0000

Data Index: 187958 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.7476. Min Act: -0.0000

Data Index: 1174055 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.7719. Min Act: -0.0000

Data Index: 103493 (C4 (Web Text))

Max Activating Token Index: 530

Text #9

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.7315. Min Act: -0.0000

Data Index: 210288 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.6934. Min Act: -0.0000

Data Index: 983429 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.6967. Min Act: -0.0000

Data Index: 1065746 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.7056. Min Act: -0.0000

Data Index: 1045050 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.7290. Min Act: -0.0000

Data Index: 732802 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.6762. Min Act: -0.0000

Data Index: 780463 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.6805. Min Act: -0.0000

Data Index: 426518 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.7133. Min Act: -0.0000

Data Index: 937645 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.6809. Min Act: -0.0000

Data Index: 1194237 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.6792. Min Act: -0.0000

Data Index: 908374 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 0.9692. Min Range: -0.9692

Max Act: 0.6733. Min Act: -0.0000

Data Index: 1154210 (C4 (Web Text))

Max Activating Token Index: 847