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

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

Neuron 1787 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2709. Min Range: -3.2709

Max Act: 3.2709. Min Act: -0.0000

Data Index: 1436632 (Python Code)

Max Activating Token Index: 974

Text #1

Max Range: 3.2709. Min Range: -3.2709

Max Act: 3.0019. Min Act: -0.0000

Data Index: 1562513 (Python Code)

Max Activating Token Index: 745

Text #2

Max Range: 3.2709. Min Range: -3.2709

Max Act: 2.9583. Min Act: -0.0000

Data Index: 1559121 (Python Code)

Max Activating Token Index: 237

Text #3

Max Range: 3.2709. Min Range: -3.2709

Max Act: 2.3915. Min Act: -0.0000

Data Index: 1518127 (Python Code)

Max Activating Token Index: 217

Text #4

Max Range: 3.2709. Min Range: -3.2709

Max Act: 2.6115. Min Act: -0.0000

Data Index: 1551387 (Python Code)

Max Activating Token Index: 974

Text #5

Max Range: 3.2709. Min Range: -3.2709

Max Act: 2.4870. Min Act: -0.0000

Data Index: 1646116 (Python Code)

Max Activating Token Index: 986

Text #6

Max Range: 3.2709. Min Range: -3.2709

Max Act: 2.5286. Min Act: -0.0000

Data Index: 1373575 (Python Code)

Max Activating Token Index: 189

Text #7

Max Range: 3.2709. Min Range: -3.2709

Max Act: 2.4840. Min Act: -0.0000

Data Index: 1426878 (Python Code)

Max Activating Token Index: 365

Text #8

Max Range: 3.2709. Min Range: -3.2709

Max Act: 2.4551. Min Act: -0.0000

Data Index: 1546827 (Python Code)

Max Activating Token Index: 1003

Text #9

Max Range: 3.2709. Min Range: -3.2709

Max Act: 2.4386. Min Act: -0.0000

Data Index: 1420606 (Python Code)

Max Activating Token Index: 790

Text #10

Max Range: 3.2709. Min Range: -3.2709

Max Act: 2.4203. Min Act: -0.0000

Data Index: 1629495 (Python Code)

Max Activating Token Index: 980

Text #11

Max Range: 3.2709. Min Range: -3.2709

Max Act: 2.2804. Min Act: -0.0000

Data Index: 1408674 (Python Code)

Max Activating Token Index: 795

Text #12

Max Range: 3.2709. Min Range: -3.2709

Max Act: 2.2930. Min Act: -0.0000

Data Index: 1412766 (Python Code)

Max Activating Token Index: 710

Text #13

Max Range: 3.2709. Min Range: -3.2709

Max Act: 2.3822. Min Act: -0.0000

Data Index: 1367354 (Python Code)

Max Activating Token Index: 268

Text #14

Max Range: 3.2709. Min Range: -3.2709

Max Act: 2.4805. Min Act: -0.0000

Data Index: 1410652 (Python Code)

Max Activating Token Index: 598

Text #15

Max Range: 3.2709. Min Range: -3.2709

Max Act: 2.3439. Min Act: -0.0000

Data Index: 1645879 (Python Code)

Max Activating Token Index: 609

Text #16

Max Range: 3.2709. Min Range: -3.2709

Max Act: 2.4556. Min Act: -0.0000

Data Index: 1576219 (Python Code)

Max Activating Token Index: 880

Text #17

Max Range: 3.2709. Min Range: -3.2709

Max Act: 2.1902. Min Act: -0.0000

Data Index: 1464836 (Python Code)

Max Activating Token Index: 211

Text #18

Max Range: 3.2709. Min Range: -3.2709

Max Act: 2.2894. Min Act: -0.0000

Data Index: 1362774 (Python Code)

Max Activating Token Index: 522

Text #19

Max Range: 3.2709. Min Range: -3.2709

Max Act: 2.1856. Min Act: -0.0000

Data Index: 1522057 (Python Code)

Max Activating Token Index: 843