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

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

Neuron 4505 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.4859. Min Act: -0.0001

Data Index: 1506853 (Python Code)

Max Activating Token Index: 198

Text #1

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.4730. Min Act: -0.0001

Data Index: 1376390 (Python Code)

Max Activating Token Index: 407

Text #2

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.3876. Min Act: -0.0001

Data Index: 1494303 (Python Code)

Max Activating Token Index: 169

Text #3

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.4183. Min Act: -0.0001

Data Index: 1481426 (Python Code)

Max Activating Token Index: 208

Text #4

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.4012. Min Act: -0.0001

Data Index: 1529778 (Python Code)

Max Activating Token Index: 18

Text #5

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.3892. Min Act: -0.0001

Data Index: 1617646 (Python Code)

Max Activating Token Index: 133

Text #6

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.3950. Min Act: -0.0001

Data Index: 1549815 (Python Code)

Max Activating Token Index: 298

Text #7

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.3688. Min Act: -0.0001

Data Index: 1575678 (Python Code)

Max Activating Token Index: 438

Text #8

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.3642. Min Act: -0.0001

Data Index: 1406116 (Python Code)

Max Activating Token Index: 258

Text #9

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.3792. Min Act: -0.0001

Data Index: 1567752 (Python Code)

Max Activating Token Index: 79

Text #10

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.3518. Min Act: -0.0001

Data Index: 1616766 (Python Code)

Max Activating Token Index: 64

Text #11

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.3744. Min Act: -0.0001

Data Index: 1501932 (Python Code)

Max Activating Token Index: 63

Text #12

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.4154. Min Act: -0.0001

Data Index: 1384106 (Python Code)

Max Activating Token Index: 76

Text #13

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.3977. Min Act: -0.0001

Data Index: 1363340 (Python Code)

Max Activating Token Index: 111

Text #14

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.3240. Min Act: -0.0001

Data Index: 1455010 (Python Code)

Max Activating Token Index: 639

Text #15

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.3840. Min Act: -0.0001

Data Index: 1408887 (Python Code)

Max Activating Token Index: 6

Text #16

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.3798. Min Act: -0.0001

Data Index: 1411688 (Python Code)

Max Activating Token Index: 27

Text #17

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.3630. Min Act: -0.0001

Data Index: 1452812 (Python Code)

Max Activating Token Index: 201

Text #18

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.3613. Min Act: -0.0001

Data Index: 1566017 (Python Code)

Max Activating Token Index: 72

Text #19

Max Range: 0.4859. Min Range: -0.4859

Max Act: 0.3685. Min Act: -0.0001

Data Index: 1466053 (Python Code)

Max Activating Token Index: 50