Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2625 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.6271. Min Act: -0.0003

Data Index: 1557636 (Python Code)

Max Activating Token Index: 538

Text #1

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.6684. Min Act: -0.0003

Data Index: 1643861 (Python Code)

Max Activating Token Index: 749

Text #2

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.6327. Min Act: -0.0003

Data Index: 1483315 (Python Code)

Max Activating Token Index: 284

Text #3

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.6237. Min Act: -0.0003

Data Index: 1653808 (Python Code)

Max Activating Token Index: 172

Text #4

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.5477. Min Act: -0.0003

Data Index: 1360120 (Python Code)

Max Activating Token Index: 1000

Text #5

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.5865. Min Act: -0.0003

Data Index: 1428773 (Python Code)

Max Activating Token Index: 682

Text #6

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.5832. Min Act: -0.0003

Data Index: 1446230 (Python Code)

Max Activating Token Index: 846

Text #7

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.5459. Min Act: -0.0003

Data Index: 1541182 (Python Code)

Max Activating Token Index: 792

Text #8

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.5784. Min Act: -0.0003

Data Index: 1506421 (Python Code)

Max Activating Token Index: 981

Text #9

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.5624. Min Act: -0.0003

Data Index: 1647564 (Python Code)

Max Activating Token Index: 808

Text #10

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.5735. Min Act: -0.0003

Data Index: 1572862 (Python Code)

Max Activating Token Index: 866

Text #11

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.5478. Min Act: -0.0003

Data Index: 1416373 (Python Code)

Max Activating Token Index: 704

Text #12

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.5937. Min Act: -0.0003

Data Index: 1637266 (Python Code)

Max Activating Token Index: 51

Text #13

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.5437. Min Act: -0.0003

Data Index: 1439692 (Python Code)

Max Activating Token Index: 718

Text #14

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.6100. Min Act: -0.0003

Data Index: 1497549 (Python Code)

Max Activating Token Index: 850

Text #15

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.5467. Min Act: -0.0003

Data Index: 1599084 (Python Code)

Max Activating Token Index: 775

Text #16

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.5845. Min Act: -0.0003

Data Index: 1627123 (Python Code)

Max Activating Token Index: 338

Text #17

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.5806. Min Act: -0.0003

Data Index: 1546142 (Python Code)

Max Activating Token Index: 191

Text #18

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.5790. Min Act: -0.0003

Data Index: 1529700 (Python Code)

Max Activating Token Index: 469

Text #19

Max Range: 0.6684. Min Range: -0.6684

Max Act: 0.5396. Min Act: -0.0003

Data Index: 1580497 (Python Code)

Max Activating Token Index: 927