Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4612 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0990. Min Act: -0.0002

Data Index: 1122588 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0918. Min Act: -0.0002

Data Index: 1136734 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0868. Min Act: -0.0002

Data Index: 1409293 (Python Code)

Max Activating Token Index: 164

Text #3

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0854. Min Act: -0.0002

Data Index: 1382163 (Python Code)

Max Activating Token Index: 526

Text #4

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0858. Min Act: -0.0002

Data Index: 1475769 (Python Code)

Max Activating Token Index: 348

Text #5

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0845. Min Act: -0.0002

Data Index: 1650051 (Python Code)

Max Activating Token Index: 599

Text #6

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0842. Min Act: -0.0002

Data Index: 1477600 (Python Code)

Max Activating Token Index: 738

Text #7

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0826. Min Act: -0.0002

Data Index: 1539382 (Python Code)

Max Activating Token Index: 887

Text #8

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0818. Min Act: -0.0002

Data Index: 1650454 (Python Code)

Max Activating Token Index: 567

Text #9

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0833. Min Act: -0.0002

Data Index: 1407898 (Python Code)

Max Activating Token Index: 732

Text #10

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0828. Min Act: -0.0002

Data Index: 1415146 (Python Code)

Max Activating Token Index: 114

Text #11

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0826. Min Act: -0.0002

Data Index: 1485494 (Python Code)

Max Activating Token Index: 155

Text #12

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0809. Min Act: -0.0002

Data Index: 1455908 (Python Code)

Max Activating Token Index: 173

Text #13

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0797. Min Act: -0.0002

Data Index: 1539257 (Python Code)

Max Activating Token Index: 982

Text #14

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0830. Min Act: -0.0002

Data Index: 1454669 (Python Code)

Max Activating Token Index: 110

Text #15

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0798. Min Act: -0.0002

Data Index: 1394763 (Python Code)

Max Activating Token Index: 846

Text #16

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0804. Min Act: -0.0002

Data Index: 1151546 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0793. Min Act: -0.0002

Data Index: 1426187 (Python Code)

Max Activating Token Index: 537

Text #18

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0807. Min Act: -0.0002

Data Index: 1576476 (Python Code)

Max Activating Token Index: 792

Text #19

Max Range: 0.0990. Min Range: -0.0990

Max Act: 0.0807. Min Act: -0.0002

Data Index: 1464284 (Python Code)

Max Activating Token Index: 406