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

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

Neuron 5189 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.5394. Min Range: -8.5394

Max Act: 8.4723. Min Act: -0.0000

Data Index: 1534539 (Python Code)

Max Activating Token Index: 101

Text #1

Max Range: 8.5394. Min Range: -8.5394

Max Act: 8.5394. Min Act: -0.0000

Data Index: 1579590 (Python Code)

Max Activating Token Index: 754

Text #2

Max Range: 8.5394. Min Range: -8.5394

Max Act: 8.3637. Min Act: -0.0000

Data Index: 1502482 (Python Code)

Max Activating Token Index: 621

Text #3

Max Range: 8.5394. Min Range: -8.5394

Max Act: 8.3491. Min Act: -0.0000

Data Index: 1482524 (Python Code)

Max Activating Token Index: 552

Text #4

Max Range: 8.5394. Min Range: -8.5394

Max Act: 7.3535. Min Act: -0.0000

Data Index: 1486288 (Python Code)

Max Activating Token Index: 823

Text #5

Max Range: 8.5394. Min Range: -8.5394

Max Act: 7.3403. Min Act: -0.0001

Data Index: 1575334 (Python Code)

Max Activating Token Index: 545

Text #6

Max Range: 8.5394. Min Range: -8.5394

Max Act: 7.3097. Min Act: -0.0001

Data Index: 1565857 (Python Code)

Max Activating Token Index: 286

Text #7

Max Range: 8.5394. Min Range: -8.5394

Max Act: 7.0915. Min Act: -0.0001

Data Index: 1510120 (Python Code)

Max Activating Token Index: 331

Text #8

Max Range: 8.5394. Min Range: -8.5394

Max Act: 6.7016. Min Act: -0.0001

Data Index: 1375860 (Python Code)

Max Activating Token Index: 503

Text #9

Max Range: 8.5394. Min Range: -8.5394

Max Act: 6.8599. Min Act: -0.0001

Data Index: 1512582 (Python Code)

Max Activating Token Index: 208

Text #10

Max Range: 8.5394. Min Range: -8.5394

Max Act: 7.0115. Min Act: -0.0001

Data Index: 1589044 (Python Code)

Max Activating Token Index: 688

Text #11

Max Range: 8.5394. Min Range: -8.5394

Max Act: 6.2638. Min Act: -0.0000

Data Index: 1519301 (Python Code)

Max Activating Token Index: 221

Text #12

Max Range: 8.5394. Min Range: -8.5394

Max Act: 6.3927. Min Act: -0.0000

Data Index: 1607521 (Python Code)

Max Activating Token Index: 59

Text #13

Max Range: 8.5394. Min Range: -8.5394

Max Act: 6.5745. Min Act: -0.0001

Data Index: 1483332 (Python Code)

Max Activating Token Index: 40

Text #14

Max Range: 8.5394. Min Range: -8.5394

Max Act: 6.0995. Min Act: -0.0001

Data Index: 1443497 (Python Code)

Max Activating Token Index: 618

Text #15

Max Range: 8.5394. Min Range: -8.5394

Max Act: 6.4468. Min Act: -0.0001

Data Index: 1475355 (Python Code)

Max Activating Token Index: 184

Text #16

Max Range: 8.5394. Min Range: -8.5394

Max Act: 6.0806. Min Act: -0.0000

Data Index: 1453048 (Python Code)

Max Activating Token Index: 190

Text #17

Max Range: 8.5394. Min Range: -8.5394

Max Act: 6.3905. Min Act: -0.0001

Data Index: 1534144 (Python Code)

Max Activating Token Index: 950

Text #18

Max Range: 8.5394. Min Range: -8.5394

Max Act: 6.5672. Min Act: -0.0001

Data Index: 1375371 (Python Code)

Max Activating Token Index: 240

Text #19

Max Range: 8.5394. Min Range: -8.5394

Max Act: 6.1812. Min Act: -0.0000

Data Index: 1395318 (Python Code)

Max Activating Token Index: 16