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

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

Neuron 4872 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.4050. Min Range: -5.4050

Max Act: 5.2201. Min Act: -0.0000

Data Index: 416019 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 5.4050. Min Range: -5.4050

Max Act: 4.9943. Min Act: -0.0000

Data Index: 717809 (C4 (Web Text))

Max Activating Token Index: 559

Text #2

Max Range: 5.4050. Min Range: -5.4050

Max Act: 5.1713. Min Act: -0.0000

Data Index: 266800 (C4 (Web Text))

Max Activating Token Index: 712

Text #3

Max Range: 5.4050. Min Range: -5.4050

Max Act: 4.8767. Min Act: -0.0000

Data Index: 300206 (C4 (Web Text))

Max Activating Token Index: 293

Text #4

Max Range: 5.4050. Min Range: -5.4050

Max Act: 5.1868. Min Act: -0.0000

Data Index: 313490 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 5.4050. Min Range: -5.4050

Max Act: 5.1693. Min Act: -0.0000

Data Index: 153362 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 5.4050. Min Range: -5.4050

Max Act: 5.1560. Min Act: -0.0000

Data Index: 767514 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 5.4050. Min Range: -5.4050

Max Act: 5.4050. Min Act: -0.0000

Data Index: 393073 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 5.4050. Min Range: -5.4050

Max Act: 5.0976. Min Act: -0.0000

Data Index: 133721 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 5.4050. Min Range: -5.4050

Max Act: 4.8654. Min Act: -0.0000

Data Index: 228752 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 5.4050. Min Range: -5.4050

Max Act: 5.1631. Min Act: -0.0000

Data Index: 33216 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 5.4050. Min Range: -5.4050

Max Act: 5.1587. Min Act: -0.0000

Data Index: 37942 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 5.4050. Min Range: -5.4050

Max Act: 5.1949. Min Act: -0.0000

Data Index: 304385 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 5.4050. Min Range: -5.4050

Max Act: 5.0188. Min Act: -0.0000

Data Index: 1281020 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 5.4050. Min Range: -5.4050

Max Act: 4.9438. Min Act: -0.0000

Data Index: 277780 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 5.4050. Min Range: -5.4050

Max Act: 5.1652. Min Act: -0.0000

Data Index: 302966 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 5.4050. Min Range: -5.4050

Max Act: 5.1774. Min Act: -0.0000

Data Index: 1246425 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 5.4050. Min Range: -5.4050

Max Act: 4.9845. Min Act: -0.0000

Data Index: 465329 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 5.4050. Min Range: -5.4050

Max Act: 4.7838. Min Act: -0.0000

Data Index: 58752 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 5.4050. Min Range: -5.4050

Max Act: 5.3318. Min Act: -0.0000

Data Index: 665145 (C4 (Web Text))

Max Activating Token Index: 711