Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 707 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0498. Min Range: -1.0498

Max Act: 1.0498. Min Act: -0.0000

Data Index: 1627142 (Python Code)

Max Activating Token Index: 20

Text #1

Max Range: 1.0498. Min Range: -1.0498

Max Act: 1.0436. Min Act: -0.0000

Data Index: 1420143 (Python Code)

Max Activating Token Index: 194

Text #2

Max Range: 1.0498. Min Range: -1.0498

Max Act: 1.0295. Min Act: -0.0000

Data Index: 1641208 (Python Code)

Max Activating Token Index: 810

Text #3

Max Range: 1.0498. Min Range: -1.0498

Max Act: 0.9602. Min Act: -0.0000

Data Index: 1550147 (Python Code)

Max Activating Token Index: 896

Text #4

Max Range: 1.0498. Min Range: -1.0498

Max Act: 0.9655. Min Act: -0.0000

Data Index: 1596631 (Python Code)

Max Activating Token Index: 890

Text #5

Max Range: 1.0498. Min Range: -1.0498

Max Act: 0.8790. Min Act: -0.0000

Data Index: 1570718 (Python Code)

Max Activating Token Index: 613

Text #6

Max Range: 1.0498. Min Range: -1.0498

Max Act: 0.9018. Min Act: -0.0000

Data Index: 1526474 (Python Code)

Max Activating Token Index: 173

Text #7

Max Range: 1.0498. Min Range: -1.0498

Max Act: 0.8729. Min Act: -0.0000

Data Index: 1625321 (Python Code)

Max Activating Token Index: 814

Text #8

Max Range: 1.0498. Min Range: -1.0498

Max Act: 0.8497. Min Act: -0.0000

Data Index: 1498908 (Python Code)

Max Activating Token Index: 537

Text #9

Max Range: 1.0498. Min Range: -1.0498

Max Act: 0.7961. Min Act: -0.0000

Data Index: 1527709 (Python Code)

Max Activating Token Index: 177

Text #10

Max Range: 1.0498. Min Range: -1.0498

Max Act: 0.8497. Min Act: -0.0000

Data Index: 1511374 (Python Code)

Max Activating Token Index: 180

Text #11

Max Range: 1.0498. Min Range: -1.0498

Max Act: 0.8162. Min Act: -0.0000

Data Index: 1511977 (Python Code)

Max Activating Token Index: 589

Text #12

Max Range: 1.0498. Min Range: -1.0498

Max Act: 0.8177. Min Act: -0.0000

Data Index: 1656724 (Python Code)

Max Activating Token Index: 702

Text #13

Max Range: 1.0498. Min Range: -1.0498

Max Act: 0.8414. Min Act: -0.0000

Data Index: 1601519 (Python Code)

Max Activating Token Index: 156

Text #14

Max Range: 1.0498. Min Range: -1.0498

Max Act: 0.8416. Min Act: -0.0000

Data Index: 1584913 (Python Code)

Max Activating Token Index: 815

Text #15

Max Range: 1.0498. Min Range: -1.0498

Max Act: 0.8493. Min Act: -0.0000

Data Index: 1609236 (Python Code)

Max Activating Token Index: 84

Text #16

Max Range: 1.0498. Min Range: -1.0498

Max Act: 0.8387. Min Act: -0.0000

Data Index: 1433594 (Python Code)

Max Activating Token Index: 974

Text #17

Max Range: 1.0498. Min Range: -1.0498

Max Act: 0.8385. Min Act: -0.0000

Data Index: 1376233 (Python Code)

Max Activating Token Index: 533

Text #18

Max Range: 1.0498. Min Range: -1.0498

Max Act: 0.8636. Min Act: -0.0000

Data Index: 1592091 (Python Code)

Max Activating Token Index: 232

Text #19

Max Range: 1.0498. Min Range: -1.0498

Max Act: 0.7858. Min Act: -0.0000

Data Index: 1557084 (Python Code)

Max Activating Token Index: 488