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

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

Neuron 468 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.6346. Min Range: -6.6346

Max Act: 6.6346. Min Act: -0.0000

Data Index: 1417635 (Python Code)

Max Activating Token Index: 180

Text #1

Max Range: 6.6346. Min Range: -6.6346

Max Act: 6.5025. Min Act: -0.0000

Data Index: 1588749 (Python Code)

Max Activating Token Index: 877

Text #2

Max Range: 6.6346. Min Range: -6.6346

Max Act: 6.1216. Min Act: -0.0000

Data Index: 488591 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 6.6346. Min Range: -6.6346

Max Act: 6.3974. Min Act: -0.0000

Data Index: 1470687 (Python Code)

Max Activating Token Index: 67

Text #4

Max Range: 6.6346. Min Range: -6.6346

Max Act: 5.9038. Min Act: -0.0000

Data Index: 1511463 (Python Code)

Max Activating Token Index: 649

Text #5

Max Range: 6.6346. Min Range: -6.6346

Max Act: 6.2931. Min Act: -0.0000

Data Index: 1298858 (C4 (Web Text))

Max Activating Token Index: 678

Text #6

Max Range: 6.6346. Min Range: -6.6346

Max Act: 6.0404. Min Act: -0.0000

Data Index: 1089078 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 6.6346. Min Range: -6.6346

Max Act: 6.0087. Min Act: -0.0000

Data Index: 99729 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 6.6346. Min Range: -6.6346

Max Act: 5.9560. Min Act: -0.0000

Data Index: 327349 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 6.6346. Min Range: -6.6346

Max Act: 6.1205. Min Act: -0.0000

Data Index: 239268 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 6.6346. Min Range: -6.6346

Max Act: 5.8808. Min Act: -0.0000

Data Index: 916584 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 6.6346. Min Range: -6.6346

Max Act: 5.8684. Min Act: -0.0000

Data Index: 1260087 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 6.6346. Min Range: -6.6346

Max Act: 5.5926. Min Act: -0.0000

Data Index: 1646269 (Python Code)

Max Activating Token Index: 693

Text #13

Max Range: 6.6346. Min Range: -6.6346

Max Act: 5.5274. Min Act: -0.0000

Data Index: 931585 (C4 (Web Text))

Max Activating Token Index: 943

Text #14

Max Range: 6.6346. Min Range: -6.6346

Max Act: 5.5020. Min Act: -0.0000

Data Index: 1649796 (Python Code)

Max Activating Token Index: 629

Text #15

Max Range: 6.6346. Min Range: -6.6346

Max Act: 5.4932. Min Act: -0.0000

Data Index: 120548 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 6.6346. Min Range: -6.6346

Max Act: 5.4193. Min Act: -0.0000

Data Index: 621484 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 6.6346. Min Range: -6.6346

Max Act: 5.3636. Min Act: -0.0000

Data Index: 915069 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 6.6346. Min Range: -6.6346

Max Act: 5.0594. Min Act: -0.0000

Data Index: 1199678 (C4 (Web Text))

Max Activating Token Index: 848

Text #19

Max Range: 6.6346. Min Range: -6.6346

Max Act: 5.3779. Min Act: -0.0000

Data Index: 1090618 (C4 (Web Text))

Max Activating Token Index: 653