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

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

Neuron 1532 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: 1.7689. Min Range: -1.7689

Max Act: 1.7689. Min Act: -0.0000

Data Index: 1592910 (Python Code)

Max Activating Token Index: 183

Text #1

Max Range: 1.7689. Min Range: -1.7689

Max Act: 1.6206. Min Act: -0.0000

Data Index: 1534219 (Python Code)

Max Activating Token Index: 615

Text #2

Max Range: 1.7689. Min Range: -1.7689

Max Act: 1.3431. Min Act: -0.0000

Data Index: 1565334 (Python Code)

Max Activating Token Index: 58

Text #3

Max Range: 1.7689. Min Range: -1.7689

Max Act: 1.4547. Min Act: -0.0000

Data Index: 1546989 (Python Code)

Max Activating Token Index: 797

Text #4

Max Range: 1.7689. Min Range: -1.7689

Max Act: 1.3991. Min Act: -0.0000

Data Index: 1581717 (Python Code)

Max Activating Token Index: 50

Text #5

Max Range: 1.7689. Min Range: -1.7689

Max Act: 1.3734. Min Act: -0.0000

Data Index: 1381835 (Python Code)

Max Activating Token Index: 481

Text #6

Max Range: 1.7689. Min Range: -1.7689

Max Act: 1.2891. Min Act: -0.0000

Data Index: 1511896 (Python Code)

Max Activating Token Index: 866

Text #7

Max Range: 1.7689. Min Range: -1.7689

Max Act: 1.2816. Min Act: -0.0000

Data Index: 1577441 (Python Code)

Max Activating Token Index: 580

Text #8

Max Range: 1.7689. Min Range: -1.7689

Max Act: 1.2987. Min Act: -0.0000

Data Index: 1471402 (Python Code)

Max Activating Token Index: 702

Text #9

Max Range: 1.7689. Min Range: -1.7689

Max Act: 1.2738. Min Act: -0.0000

Data Index: 739292 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 1.7689. Min Range: -1.7689

Max Act: 1.2777. Min Act: -0.0000

Data Index: 1432134 (Python Code)

Max Activating Token Index: 864

Text #11

Max Range: 1.7689. Min Range: -1.7689

Max Act: 1.2665. Min Act: -0.0000

Data Index: 1472768 (Python Code)

Max Activating Token Index: 889

Text #12

Max Range: 1.7689. Min Range: -1.7689

Max Act: 1.3309. Min Act: -0.0000

Data Index: 1600447 (Python Code)

Max Activating Token Index: 585

Text #13

Max Range: 1.7689. Min Range: -1.7689

Max Act: 1.2618. Min Act: -0.0000

Data Index: 1487091 (Python Code)

Max Activating Token Index: 642

Text #14

Max Range: 1.7689. Min Range: -1.7689

Max Act: 1.2473. Min Act: -0.0000

Data Index: 1547505 (Python Code)

Max Activating Token Index: 54

Text #15

Max Range: 1.7689. Min Range: -1.7689

Max Act: 1.1672. Min Act: -0.0000

Data Index: 1510922 (Python Code)

Max Activating Token Index: 785

Text #16

Max Range: 1.7689. Min Range: -1.7689

Max Act: 1.2171. Min Act: -0.0000

Data Index: 1509436 (Python Code)

Max Activating Token Index: 552

Text #17

Max Range: 1.7689. Min Range: -1.7689

Max Act: 1.1814. Min Act: -0.0000

Data Index: 1616669 (Python Code)

Max Activating Token Index: 260

Text #18

Max Range: 1.7689. Min Range: -1.7689

Max Act: 1.1355. Min Act: -0.0000

Data Index: 1615492 (Python Code)

Max Activating Token Index: 843

Text #19

Max Range: 1.7689. Min Range: -1.7689

Max Act: 1.2013. Min Act: -0.0000

Data Index: 1417269 (Python Code)

Max Activating Token Index: 70