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

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

Neuron 1238 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8844. Min Range: -2.8844

Max Act: 2.8844. Min Act: -0.0000

Data Index: 1605058 (Python Code)

Max Activating Token Index: 671

Text #1

Max Range: 2.8844. Min Range: -2.8844

Max Act: 2.7682. Min Act: -0.0000

Data Index: 1384658 (Python Code)

Max Activating Token Index: 989

Text #2

Max Range: 2.8844. Min Range: -2.8844

Max Act: 2.6604. Min Act: -0.0000

Data Index: 1523124 (Python Code)

Max Activating Token Index: 642

Text #3

Max Range: 2.8844. Min Range: -2.8844

Max Act: 2.5919. Min Act: -0.0000

Data Index: 1402582 (Python Code)

Max Activating Token Index: 639

Text #4

Max Range: 2.8844. Min Range: -2.8844

Max Act: 2.7149. Min Act: -0.0000

Data Index: 1650791 (Python Code)

Max Activating Token Index: 762

Text #5

Max Range: 2.8844. Min Range: -2.8844

Max Act: 2.4195. Min Act: -0.0000

Data Index: 1460701 (Python Code)

Max Activating Token Index: 896

Text #6

Max Range: 2.8844. Min Range: -2.8844

Max Act: 2.6706. Min Act: -0.0000

Data Index: 1431451 (Python Code)

Max Activating Token Index: 917

Text #7

Max Range: 2.8844. Min Range: -2.8844

Max Act: 2.5235. Min Act: -0.0000

Data Index: 1368031 (Python Code)

Max Activating Token Index: 559

Text #8

Max Range: 2.8844. Min Range: -2.8844

Max Act: 2.6457. Min Act: -0.0000

Data Index: 1489242 (Python Code)

Max Activating Token Index: 420

Text #9

Max Range: 2.8844. Min Range: -2.8844

Max Act: 2.5374. Min Act: -0.0000

Data Index: 1440867 (Python Code)

Max Activating Token Index: 753

Text #10

Max Range: 2.8844. Min Range: -2.8844

Max Act: 2.6295. Min Act: -0.0000

Data Index: 1455114 (Python Code)

Max Activating Token Index: 636

Text #11

Max Range: 2.8844. Min Range: -2.8844

Max Act: 2.7482. Min Act: -0.0000

Data Index: 1407979 (Python Code)

Max Activating Token Index: 963

Text #12

Max Range: 2.8844. Min Range: -2.8844

Max Act: 2.3793. Min Act: -0.0000

Data Index: 1639787 (Python Code)

Max Activating Token Index: 954

Text #13

Max Range: 2.8844. Min Range: -2.8844

Max Act: 2.5909. Min Act: -0.0000

Data Index: 1433254 (Python Code)

Max Activating Token Index: 923

Text #14

Max Range: 2.8844. Min Range: -2.8844

Max Act: 2.4683. Min Act: -0.0000

Data Index: 1585935 (Python Code)

Max Activating Token Index: 293

Text #15

Max Range: 2.8844. Min Range: -2.8844

Max Act: 2.6078. Min Act: -0.0000

Data Index: 1563881 (Python Code)

Max Activating Token Index: 438

Text #16

Max Range: 2.8844. Min Range: -2.8844

Max Act: 2.4340. Min Act: -0.0000

Data Index: 1615816 (Python Code)

Max Activating Token Index: 879

Text #17

Max Range: 2.8844. Min Range: -2.8844

Max Act: 2.4959. Min Act: -0.0000

Data Index: 1466929 (Python Code)

Max Activating Token Index: 833

Text #18

Max Range: 2.8844. Min Range: -2.8844

Max Act: 2.5804. Min Act: -0.0000

Data Index: 1616622 (Python Code)

Max Activating Token Index: 708

Text #19

Max Range: 2.8844. Min Range: -2.8844

Max Act: 2.4471. Min Act: -0.0000

Data Index: 1446616 (Python Code)

Max Activating Token Index: 216