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

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

Neuron 3792 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4370. Min Range: -0.4370

Max Act: 0.4370. Min Act: -0.0001

Data Index: 1590694 (Python Code)

Max Activating Token Index: 418

Text #1

Max Range: 0.4370. Min Range: -0.4370

Max Act: 0.4053. Min Act: -0.0000

Data Index: 1556794 (Python Code)

Max Activating Token Index: 664

Text #2

Max Range: 0.4370. Min Range: -0.4370

Max Act: 0.3733. Min Act: -0.0000

Data Index: 1526336 (Python Code)

Max Activating Token Index: 918

Text #3

Max Range: 0.4370. Min Range: -0.4370

Max Act: 0.3423. Min Act: -0.0001

Data Index: 1502096 (Python Code)

Max Activating Token Index: 554

Text #4

Max Range: 0.4370. Min Range: -0.4370

Max Act: 0.3294. Min Act: -0.0000

Data Index: 1547222 (Python Code)

Max Activating Token Index: 194

Text #5

Max Range: 0.4370. Min Range: -0.4370

Max Act: 0.3048. Min Act: -0.0000

Data Index: 1362493 (Python Code)

Max Activating Token Index: 759

Text #6

Max Range: 0.4370. Min Range: -0.4370

Max Act: 0.3153. Min Act: -0.0000

Data Index: 1613085 (Python Code)

Max Activating Token Index: 722

Text #7

Max Range: 0.4370. Min Range: -0.4370

Max Act: 0.2794. Min Act: -0.0000

Data Index: 1534463 (Python Code)

Max Activating Token Index: 956

Text #8

Max Range: 0.4370. Min Range: -0.4370

Max Act: 0.2795. Min Act: -0.0001

Data Index: 1573714 (Python Code)

Max Activating Token Index: 326

Text #9

Max Range: 0.4370. Min Range: -0.4370

Max Act: 0.2762. Min Act: -0.0001

Data Index: 1417554 (Python Code)

Max Activating Token Index: 318

Text #10

Max Range: 0.4370. Min Range: -0.4370

Max Act: 0.2667. Min Act: -0.0001

Data Index: 1411131 (Python Code)

Max Activating Token Index: 155

Text #11

Max Range: 0.4370. Min Range: -0.4370

Max Act: 0.2721. Min Act: -0.0000

Data Index: 1635352 (Python Code)

Max Activating Token Index: 525

Text #12

Max Range: 0.4370. Min Range: -0.4370

Max Act: 0.2561. Min Act: -0.0001

Data Index: 1538264 (Python Code)

Max Activating Token Index: 956

Text #13

Max Range: 0.4370. Min Range: -0.4370

Max Act: 0.2560. Min Act: -0.0001

Data Index: 1438318 (Python Code)

Max Activating Token Index: 215

Text #14

Max Range: 0.4370. Min Range: -0.4370

Max Act: 0.2481. Min Act: -0.0001

Data Index: 1494506 (Python Code)

Max Activating Token Index: 821

Text #15

Max Range: 0.4370. Min Range: -0.4370

Max Act: 0.2644. Min Act: -0.0000

Data Index: 1162581 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 0.4370. Min Range: -0.4370

Max Act: 0.2473. Min Act: -0.0000

Data Index: 1646005 (Python Code)

Max Activating Token Index: 195

Text #17

Max Range: 0.4370. Min Range: -0.4370

Max Act: 0.2520. Min Act: -0.0001

Data Index: 1412724 (Python Code)

Max Activating Token Index: 418

Text #18

Max Range: 0.4370. Min Range: -0.4370

Max Act: 0.2536. Min Act: -0.0001

Data Index: 1493539 (Python Code)

Max Activating Token Index: 182

Text #19

Max Range: 0.4370. Min Range: -0.4370

Max Act: 0.2522. Min Act: -0.0001

Data Index: 1655372 (Python Code)

Max Activating Token Index: 37