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

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

Neuron 3812 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4055. Min Range: -2.4055

Max Act: 2.3102. Min Act: -0.0000

Data Index: 1438146 (Python Code)

Max Activating Token Index: 570

Text #1

Max Range: 2.4055. Min Range: -2.4055

Max Act: 2.3550. Min Act: -0.0000

Data Index: 1423123 (Python Code)

Max Activating Token Index: 816

Text #2

Max Range: 2.4055. Min Range: -2.4055

Max Act: 2.4055. Min Act: -0.0000

Data Index: 1551743 (Python Code)

Max Activating Token Index: 348

Text #3

Max Range: 2.4055. Min Range: -2.4055

Max Act: 2.2790. Min Act: -0.0000

Data Index: 1438705 (Python Code)

Max Activating Token Index: 430

Text #4

Max Range: 2.4055. Min Range: -2.4055

Max Act: 2.2689. Min Act: -0.0000

Data Index: 1433766 (Python Code)

Max Activating Token Index: 768

Text #5

Max Range: 2.4055. Min Range: -2.4055

Max Act: 2.2588. Min Act: -0.0000

Data Index: 1590667 (Python Code)

Max Activating Token Index: 329

Text #6

Max Range: 2.4055. Min Range: -2.4055

Max Act: 2.1237. Min Act: -0.0000

Data Index: 1435612 (Python Code)

Max Activating Token Index: 670

Text #7

Max Range: 2.4055. Min Range: -2.4055

Max Act: 2.2309. Min Act: -0.0000

Data Index: 1443262 (Python Code)

Max Activating Token Index: 138

Text #8

Max Range: 2.4055. Min Range: -2.4055

Max Act: 1.9725. Min Act: -0.0000

Data Index: 1656871 (Python Code)

Max Activating Token Index: 739

Text #9

Max Range: 2.4055. Min Range: -2.4055

Max Act: 2.0751. Min Act: -0.0000

Data Index: 1553517 (Python Code)

Max Activating Token Index: 431

Text #10

Max Range: 2.4055. Min Range: -2.4055

Max Act: 2.0550. Min Act: -0.0000

Data Index: 1469071 (Python Code)

Max Activating Token Index: 96

Text #11

Max Range: 2.4055. Min Range: -2.4055

Max Act: 2.1302. Min Act: -0.0000

Data Index: 1549949 (Python Code)

Max Activating Token Index: 783

Text #12

Max Range: 2.4055. Min Range: -2.4055

Max Act: 2.0837. Min Act: -0.0000

Data Index: 1535580 (Python Code)

Max Activating Token Index: 472

Text #13

Max Range: 2.4055. Min Range: -2.4055

Max Act: 1.9458. Min Act: -0.0000

Data Index: 1548127 (Python Code)

Max Activating Token Index: 892

Text #14

Max Range: 2.4055. Min Range: -2.4055

Max Act: 1.9756. Min Act: -0.0000

Data Index: 1508200 (Python Code)

Max Activating Token Index: 443

Text #15

Max Range: 2.4055. Min Range: -2.4055

Max Act: 2.0956. Min Act: -0.0000

Data Index: 1363810 (Python Code)

Max Activating Token Index: 617

Text #16

Max Range: 2.4055. Min Range: -2.4055

Max Act: 1.8709. Min Act: -0.0000

Data Index: 1652411 (Python Code)

Max Activating Token Index: 733

Text #17

Max Range: 2.4055. Min Range: -2.4055

Max Act: 1.9619. Min Act: -0.0000

Data Index: 1484679 (Python Code)

Max Activating Token Index: 518

Text #18

Max Range: 2.4055. Min Range: -2.4055

Max Act: 1.9072. Min Act: -0.0000

Data Index: 1456792 (Python Code)

Max Activating Token Index: 774

Text #19

Max Range: 2.4055. Min Range: -2.4055

Max Act: 1.8835. Min Act: -0.0000

Data Index: 1456294 (Python Code)

Max Activating Token Index: 650