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

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

Neuron 3097 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: 1.3488. Min Range: -1.3488

Max Act: 1.3488. Min Act: -0.0000

Data Index: 14891 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 1.3488. Min Range: -1.3488

Max Act: 1.2682. Min Act: -0.0000

Data Index: 1499503 (Python Code)

Max Activating Token Index: 677

Text #2

Max Range: 1.3488. Min Range: -1.3488

Max Act: 1.0544. Min Act: -0.0000

Data Index: 1032890 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 1.3488. Min Range: -1.3488

Max Act: 1.0400. Min Act: -0.0000

Data Index: 801080 (C4 (Web Text))

Max Activating Token Index: 863

Text #4

Max Range: 1.3488. Min Range: -1.3488

Max Act: 1.0963. Min Act: -0.0000

Data Index: 735392 (C4 (Web Text))

Max Activating Token Index: 994

Text #5

Max Range: 1.3488. Min Range: -1.3488

Max Act: 1.0717. Min Act: -0.0000

Data Index: 894395 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 1.3488. Min Range: -1.3488

Max Act: 1.0708. Min Act: -0.0000

Data Index: 1034702 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 1.3488. Min Range: -1.3488

Max Act: 1.0652. Min Act: -0.0000

Data Index: 1097885 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 1.3488. Min Range: -1.3488

Max Act: 1.0515. Min Act: -0.0000

Data Index: 594050 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 1.3488. Min Range: -1.3488

Max Act: 1.1111. Min Act: -0.0000

Data Index: 648718 (C4 (Web Text))

Max Activating Token Index: 645

Text #10

Max Range: 1.3488. Min Range: -1.3488

Max Act: 1.0025. Min Act: -0.0000

Data Index: 1541921 (Python Code)

Max Activating Token Index: 730

Text #11

Max Range: 1.3488. Min Range: -1.3488

Max Act: 0.9634. Min Act: -0.0000

Data Index: 12470 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 1.3488. Min Range: -1.3488

Max Act: 1.0278. Min Act: -0.0000

Data Index: 436119 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 1.3488. Min Range: -1.3488

Max Act: 1.0335. Min Act: -0.0000

Data Index: 1470338 (Python Code)

Max Activating Token Index: 859

Text #14

Max Range: 1.3488. Min Range: -1.3488

Max Act: 1.0693. Min Act: -0.0000

Data Index: 834598 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 1.3488. Min Range: -1.3488

Max Act: 1.0723. Min Act: -0.0000

Data Index: 1140024 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 1.3488. Min Range: -1.3488

Max Act: 1.0201. Min Act: -0.0000

Data Index: 1547771 (Python Code)

Max Activating Token Index: 388

Text #17

Max Range: 1.3488. Min Range: -1.3488

Max Act: 1.0644. Min Act: -0.0000

Data Index: 466348 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 1.3488. Min Range: -1.3488

Max Act: 0.9945. Min Act: -0.0000

Data Index: 18112 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 1.3488. Min Range: -1.3488

Max Act: 1.0005. Min Act: -0.0000

Data Index: 1186625 (C4 (Web Text))

Max Activating Token Index: 429