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

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

Neuron 4781 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2815. Min Range: -4.2815

Max Act: 4.2815. Min Act: -0.0000

Data Index: 1607671 (Python Code)

Max Activating Token Index: 1019

Text #1

Max Range: 4.2815. Min Range: -4.2815

Max Act: 3.9510. Min Act: -0.0000

Data Index: 1469840 (Python Code)

Max Activating Token Index: 984

Text #2

Max Range: 4.2815. Min Range: -4.2815

Max Act: 3.8013. Min Act: -0.0000

Data Index: 1424538 (Python Code)

Max Activating Token Index: 796

Text #3

Max Range: 4.2815. Min Range: -4.2815

Max Act: 3.6503. Min Act: -0.0000

Data Index: 1608341 (Python Code)

Max Activating Token Index: 548

Text #4

Max Range: 4.2815. Min Range: -4.2815

Max Act: 3.4738. Min Act: -0.0000

Data Index: 1530313 (Python Code)

Max Activating Token Index: 215

Text #5

Max Range: 4.2815. Min Range: -4.2815

Max Act: 3.4511. Min Act: -0.0000

Data Index: 1640454 (Python Code)

Max Activating Token Index: 388

Text #6

Max Range: 4.2815. Min Range: -4.2815

Max Act: 3.0974. Min Act: -0.0000

Data Index: 1583006 (Python Code)

Max Activating Token Index: 667

Text #7

Max Range: 4.2815. Min Range: -4.2815

Max Act: 3.1635. Min Act: -0.0000

Data Index: 1531845 (Python Code)

Max Activating Token Index: 703

Text #8

Max Range: 4.2815. Min Range: -4.2815

Max Act: 3.1329. Min Act: -0.0000

Data Index: 1461267 (Python Code)

Max Activating Token Index: 455

Text #9

Max Range: 4.2815. Min Range: -4.2815

Max Act: 3.0559. Min Act: -0.0000

Data Index: 1582778 (Python Code)

Max Activating Token Index: 225

Text #10

Max Range: 4.2815. Min Range: -4.2815

Max Act: 2.9413. Min Act: -0.0000

Data Index: 1388545 (Python Code)

Max Activating Token Index: 298

Text #11

Max Range: 4.2815. Min Range: -4.2815

Max Act: 3.0041. Min Act: -0.0000

Data Index: 1510116 (Python Code)

Max Activating Token Index: 979

Text #12

Max Range: 4.2815. Min Range: -4.2815

Max Act: 2.7964. Min Act: -0.0000

Data Index: 1595908 (Python Code)

Max Activating Token Index: 394

Text #13

Max Range: 4.2815. Min Range: -4.2815

Max Act: 2.8719. Min Act: -0.0000

Data Index: 1456866 (Python Code)

Max Activating Token Index: 15

Text #14

Max Range: 4.2815. Min Range: -4.2815

Max Act: 2.8664. Min Act: -0.0000

Data Index: 1538090 (Python Code)

Max Activating Token Index: 619

Text #15

Max Range: 4.2815. Min Range: -4.2815

Max Act: 2.9803. Min Act: -0.0000

Data Index: 1409062 (Python Code)

Max Activating Token Index: 237

Text #16

Max Range: 4.2815. Min Range: -4.2815

Max Act: 2.6529. Min Act: -0.0000

Data Index: 1624732 (Python Code)

Max Activating Token Index: 165

Text #17

Max Range: 4.2815. Min Range: -4.2815

Max Act: 2.7765. Min Act: -0.0000

Data Index: 1433524 (Python Code)

Max Activating Token Index: 391

Text #18

Max Range: 4.2815. Min Range: -4.2815

Max Act: 2.7324. Min Act: -0.0000

Data Index: 1521737 (Python Code)

Max Activating Token Index: 132

Text #19

Max Range: 4.2815. Min Range: -4.2815

Max Act: 2.6817. Min Act: -0.0000

Data Index: 1599269 (Python Code)

Max Activating Token Index: 924