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

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

Neuron 1479 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: 0.5599. Min Range: -0.5599

Max Act: 0.5599. Min Act: -0.0000

Data Index: 1112592 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.5128. Min Act: -0.0000

Data Index: 709886 (C4 (Web Text))

Max Activating Token Index: 519

Text #2

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.4970. Min Act: -0.0000

Data Index: 1618860 (Python Code)

Max Activating Token Index: 363

Text #3

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.4696. Min Act: -0.0000

Data Index: 1454721 (Python Code)

Max Activating Token Index: 714

Text #4

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.4568. Min Act: -0.0000

Data Index: 810383 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.4579. Min Act: -0.0000

Data Index: 328152 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.4537. Min Act: -0.0000

Data Index: 568985 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.4208. Min Act: -0.0000

Data Index: 372725 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.4273. Min Act: -0.0000

Data Index: 1538869 (Python Code)

Max Activating Token Index: 874

Text #9

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.4024. Min Act: -0.0000

Data Index: 1053101 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.4074. Min Act: -0.0000

Data Index: 1522790 (Python Code)

Max Activating Token Index: 82

Text #11

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.4000. Min Act: -0.0000

Data Index: 87824 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.3758. Min Act: 0.0000

Data Index: 943633 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.4052. Min Act: -0.0000

Data Index: 738974 (C4 (Web Text))

Max Activating Token Index: 762

Text #14

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.3730. Min Act: -0.0000

Data Index: 421049 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.3773. Min Act: -0.0000

Data Index: 809752 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.3614. Min Act: -0.0000

Data Index: 1152555 (C4 (Web Text))

Max Activating Token Index: 842

Text #17

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.3699. Min Act: -0.0000

Data Index: 633689 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.3781. Min Act: -0.0000

Data Index: 86648 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 0.5599. Min Range: -0.5599

Max Act: 0.3540. Min Act: -0.0000

Data Index: 268487 (C4 (Web Text))

Max Activating Token Index: 401