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

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

Neuron 4422 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3688. Min Range: -1.3688

Max Act: 1.3313. Min Act: -0.0000

Data Index: 1571560 (Python Code)

Max Activating Token Index: 776

Text #1

Max Range: 1.3688. Min Range: -1.3688

Max Act: 1.3688. Min Act: -0.0000

Data Index: 1463995 (Python Code)

Max Activating Token Index: 608

Text #2

Max Range: 1.3688. Min Range: -1.3688

Max Act: 1.3492. Min Act: -0.0000

Data Index: 1472357 (Python Code)

Max Activating Token Index: 220

Text #3

Max Range: 1.3688. Min Range: -1.3688

Max Act: 1.2513. Min Act: -0.0000

Data Index: 1475751 (Python Code)

Max Activating Token Index: 425

Text #4

Max Range: 1.3688. Min Range: -1.3688

Max Act: 1.1624. Min Act: -0.0000

Data Index: 1605385 (Python Code)

Max Activating Token Index: 272

Text #5

Max Range: 1.3688. Min Range: -1.3688

Max Act: 1.1268. Min Act: -0.0000

Data Index: 1620801 (Python Code)

Max Activating Token Index: 539

Text #6

Max Range: 1.3688. Min Range: -1.3688

Max Act: 0.9925. Min Act: -0.0000

Data Index: 1577220 (Python Code)

Max Activating Token Index: 643

Text #7

Max Range: 1.3688. Min Range: -1.3688

Max Act: 1.1380. Min Act: -0.0000

Data Index: 1559426 (Python Code)

Max Activating Token Index: 466

Text #8

Max Range: 1.3688. Min Range: -1.3688

Max Act: 1.0763. Min Act: -0.0000

Data Index: 1602963 (Python Code)

Max Activating Token Index: 701

Text #9

Max Range: 1.3688. Min Range: -1.3688

Max Act: 0.9902. Min Act: -0.0000

Data Index: 1025813 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 1.3688. Min Range: -1.3688

Max Act: 1.0865. Min Act: -0.0000

Data Index: 1528820 (Python Code)

Max Activating Token Index: 748

Text #11

Max Range: 1.3688. Min Range: -1.3688

Max Act: 1.0567. Min Act: -0.0000

Data Index: 1369655 (Python Code)

Max Activating Token Index: 61

Text #12

Max Range: 1.3688. Min Range: -1.3688

Max Act: 1.0078. Min Act: -0.0000

Data Index: 1630306 (Python Code)

Max Activating Token Index: 83

Text #13

Max Range: 1.3688. Min Range: -1.3688

Max Act: 0.9717. Min Act: -0.0000

Data Index: 1647232 (Python Code)

Max Activating Token Index: 652

Text #14

Max Range: 1.3688. Min Range: -1.3688

Max Act: 0.9819. Min Act: -0.0000

Data Index: 1465805 (Python Code)

Max Activating Token Index: 659

Text #15

Max Range: 1.3688. Min Range: -1.3688

Max Act: 0.9767. Min Act: -0.0000

Data Index: 1388020 (Python Code)

Max Activating Token Index: 980

Text #16

Max Range: 1.3688. Min Range: -1.3688

Max Act: 0.9693. Min Act: -0.0000

Data Index: 1589643 (Python Code)

Max Activating Token Index: 215

Text #17

Max Range: 1.3688. Min Range: -1.3688

Max Act: 1.0078. Min Act: -0.0000

Data Index: 1418955 (Python Code)

Max Activating Token Index: 223

Text #18

Max Range: 1.3688. Min Range: -1.3688

Max Act: 0.9712. Min Act: -0.0000

Data Index: 1566986 (Python Code)

Max Activating Token Index: 75

Text #19

Max Range: 1.3688. Min Range: -1.3688

Max Act: 1.0251. Min Act: -0.0000

Data Index: 1425236 (Python Code)

Max Activating Token Index: 439