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

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

Neuron 3063 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3868. Min Range: -1.3868

Max Act: 1.3756. Min Act: -0.0000

Data Index: 805177 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 1.3868. Min Range: -1.3868

Max Act: 1.2911. Min Act: -0.0000

Data Index: 958002 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 1.3868. Min Range: -1.3868

Max Act: 1.3868. Min Act: -0.0000

Data Index: 167291 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 1.3868. Min Range: -1.3868

Max Act: 1.3455. Min Act: -0.0000

Data Index: 940724 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 1.3868. Min Range: -1.3868

Max Act: 1.2677. Min Act: -0.0000

Data Index: 936917 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 1.3868. Min Range: -1.3868

Max Act: 1.2125. Min Act: -0.0000

Data Index: 994907 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 1.3868. Min Range: -1.3868

Max Act: 1.1980. Min Act: -0.0000

Data Index: 1284997 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 1.3868. Min Range: -1.3868

Max Act: 1.2121. Min Act: -0.0000

Data Index: 139388 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 1.3868. Min Range: -1.3868

Max Act: 1.2557. Min Act: -0.0000

Data Index: 765796 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 1.3868. Min Range: -1.3868

Max Act: 1.1666. Min Act: -0.0000

Data Index: 645610 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 1.3868. Min Range: -1.3868

Max Act: 1.1559. Min Act: -0.0000

Data Index: 792891 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 1.3868. Min Range: -1.3868

Max Act: 1.1301. Min Act: -0.0000

Data Index: 1150159 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 1.3868. Min Range: -1.3868

Max Act: 1.1365. Min Act: -0.0000

Data Index: 79188 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 1.3868. Min Range: -1.3868

Max Act: 1.1323. Min Act: -0.0000

Data Index: 897057 (C4 (Web Text))

Max Activating Token Index: 922

Text #14

Max Range: 1.3868. Min Range: -1.3868

Max Act: 1.1233. Min Act: -0.0000

Data Index: 165912 (C4 (Web Text))

Max Activating Token Index: 590

Text #15

Max Range: 1.3868. Min Range: -1.3868

Max Act: 1.1509. Min Act: -0.0000

Data Index: 443273 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 1.3868. Min Range: -1.3868

Max Act: 1.1562. Min Act: -0.0000

Data Index: 1093132 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 1.3868. Min Range: -1.3868

Max Act: 0.9710. Min Act: -0.0000

Data Index: 367662 (C4 (Web Text))

Max Activating Token Index: 954

Text #18

Max Range: 1.3868. Min Range: -1.3868

Max Act: 1.0328. Min Act: -0.0000

Data Index: 1285104 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 1.3868. Min Range: -1.3868

Max Act: 0.9736. Min Act: -0.0000

Data Index: 1141640 (C4 (Web Text))

Max Activating Token Index: 498