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

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

Neuron 5627 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3718. Min Range: -2.3718

Max Act: 2.3718. Min Act: -0.0000

Data Index: 1461624 (Python Code)

Max Activating Token Index: 1005

Text #1

Max Range: 2.3718. Min Range: -2.3718

Max Act: 2.0737. Min Act: -0.0000

Data Index: 1449760 (Python Code)

Max Activating Token Index: 366

Text #2

Max Range: 2.3718. Min Range: -2.3718

Max Act: 1.8647. Min Act: -0.0000

Data Index: 1517727 (Python Code)

Max Activating Token Index: 280

Text #3

Max Range: 2.3718. Min Range: -2.3718

Max Act: 1.5579. Min Act: -0.0000

Data Index: 1634771 (Python Code)

Max Activating Token Index: 482

Text #4

Max Range: 2.3718. Min Range: -2.3718

Max Act: 1.5631. Min Act: -0.0000

Data Index: 1369789 (Python Code)

Max Activating Token Index: 570

Text #5

Max Range: 2.3718. Min Range: -2.3718

Max Act: 1.3772. Min Act: -0.0000

Data Index: 1535523 (Python Code)

Max Activating Token Index: 749

Text #6

Max Range: 2.3718. Min Range: -2.3718

Max Act: 1.4360. Min Act: -0.0000

Data Index: 1390145 (Python Code)

Max Activating Token Index: 315

Text #7

Max Range: 2.3718. Min Range: -2.3718

Max Act: 1.4275. Min Act: -0.0000

Data Index: 1379706 (Python Code)

Max Activating Token Index: 958

Text #8

Max Range: 2.3718. Min Range: -2.3718

Max Act: 1.3872. Min Act: -0.0000

Data Index: 1572870 (Python Code)

Max Activating Token Index: 210

Text #9

Max Range: 2.3718. Min Range: -2.3718

Max Act: 1.4599. Min Act: -0.0000

Data Index: 1466023 (Python Code)

Max Activating Token Index: 907

Text #10

Max Range: 2.3718. Min Range: -2.3718

Max Act: 1.2453. Min Act: -0.0000

Data Index: 1384698 (Python Code)

Max Activating Token Index: 414

Text #11

Max Range: 2.3718. Min Range: -2.3718

Max Act: 1.4360. Min Act: -0.0000

Data Index: 1601218 (Python Code)

Max Activating Token Index: 652

Text #12

Max Range: 2.3718. Min Range: -2.3718

Max Act: 1.3350. Min Act: -0.0000

Data Index: 1447273 (Python Code)

Max Activating Token Index: 625

Text #13

Max Range: 2.3718. Min Range: -2.3718

Max Act: 1.2935. Min Act: -0.0000

Data Index: 1576167 (Python Code)

Max Activating Token Index: 457

Text #14

Max Range: 2.3718. Min Range: -2.3718

Max Act: 1.3831. Min Act: -0.0000

Data Index: 1642536 (Python Code)

Max Activating Token Index: 630

Text #15

Max Range: 2.3718. Min Range: -2.3718

Max Act: 1.2643. Min Act: -0.0000

Data Index: 1409744 (Python Code)

Max Activating Token Index: 456

Text #16

Max Range: 2.3718. Min Range: -2.3718

Max Act: 1.2566. Min Act: -0.0000

Data Index: 1653222 (Python Code)

Max Activating Token Index: 630

Text #17

Max Range: 2.3718. Min Range: -2.3718

Max Act: 1.2898. Min Act: -0.0000

Data Index: 1627073 (Python Code)

Max Activating Token Index: 626

Text #18

Max Range: 2.3718. Min Range: -2.3718

Max Act: 1.1826. Min Act: -0.0000

Data Index: 1560805 (Python Code)

Max Activating Token Index: 864

Text #19

Max Range: 2.3718. Min Range: -2.3718

Max Act: 1.2650. Min Act: -0.0000

Data Index: 1513738 (Python Code)

Max Activating Token Index: 86