Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 8 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0977. Min Act: -0.0001

Data Index: 398513 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0929. Min Act: -0.0001

Data Index: 1503933 (Python Code)

Max Activating Token Index: 154

Text #2

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0852. Min Act: -0.0001

Data Index: 1579622 (Python Code)

Max Activating Token Index: 81

Text #3

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0874. Min Act: -0.0001

Data Index: 257067 (C4 (Web Text))

Max Activating Token Index: 649

Text #4

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0883. Min Act: -0.0001

Data Index: 1528887 (Python Code)

Max Activating Token Index: 385

Text #5

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0838. Min Act: -0.0001

Data Index: 1387580 (Python Code)

Max Activating Token Index: 103

Text #6

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0705. Min Act: -0.0001

Data Index: 1515574 (Python Code)

Max Activating Token Index: 879

Text #7

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0740. Min Act: -0.0001

Data Index: 1554906 (Python Code)

Max Activating Token Index: 1022

Text #8

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0780. Min Act: -0.0001

Data Index: 1415413 (Python Code)

Max Activating Token Index: 101

Text #9

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0756. Min Act: -0.0001

Data Index: 1409959 (Python Code)

Max Activating Token Index: 152

Text #10

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0738. Min Act: -0.0001

Data Index: 1519891 (Python Code)

Max Activating Token Index: 126

Text #11

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0715. Min Act: -0.0001

Data Index: 1505948 (Python Code)

Max Activating Token Index: 386

Text #12

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0770. Min Act: -0.0001

Data Index: 1388607 (Python Code)

Max Activating Token Index: 753

Text #13

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0731. Min Act: -0.0001

Data Index: 1477617 (Python Code)

Max Activating Token Index: 486

Text #14

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0736. Min Act: -0.0001

Data Index: 1635781 (Python Code)

Max Activating Token Index: 261

Text #15

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0711. Min Act: -0.0001

Data Index: 1404206 (Python Code)

Max Activating Token Index: 836

Text #16

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0737. Min Act: -0.0001

Data Index: 1395016 (Python Code)

Max Activating Token Index: 180

Text #17

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0678. Min Act: -0.0001

Data Index: 387801 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0730. Min Act: -0.0001

Data Index: 1625919 (Python Code)

Max Activating Token Index: 192

Text #19

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0724. Min Act: -0.0001

Data Index: 1423529 (Python Code)

Max Activating Token Index: 266