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

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

Neuron 1655 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: 0.0993. Min Range: -0.0993

Max Act: 0.0993. Min Act: -0.0002

Data Index: 1643987 (Python Code)

Max Activating Token Index: 300

Text #1

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0880. Min Act: -0.0002

Data Index: 576928 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0886. Min Act: -0.0002

Data Index: 1136232 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0858. Min Act: -0.0002

Data Index: 1635387 (Python Code)

Max Activating Token Index: 130

Text #4

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0842. Min Act: -0.0002

Data Index: 196645 (C4 (Web Text))

Max Activating Token Index: 612

Text #5

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0832. Min Act: -0.0002

Data Index: 154295 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0827. Min Act: -0.0002

Data Index: 206754 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0839. Min Act: -0.0002

Data Index: 1604614 (Python Code)

Max Activating Token Index: 202

Text #8

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0829. Min Act: -0.0002

Data Index: 1051191 (C4 (Web Text))

Max Activating Token Index: 659

Text #9

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0843. Min Act: -0.0002

Data Index: 1385527 (Python Code)

Max Activating Token Index: 761

Text #10

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0849. Min Act: -0.0002

Data Index: 172738 (C4 (Web Text))

Max Activating Token Index: 828

Text #11

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0837. Min Act: -0.0002

Data Index: 1390215 (Python Code)

Max Activating Token Index: 102

Text #12

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0833. Min Act: -0.0002

Data Index: 450080 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0834. Min Act: -0.0002

Data Index: 885417 (C4 (Web Text))

Max Activating Token Index: 643

Text #14

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0824. Min Act: -0.0002

Data Index: 454215 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0824. Min Act: -0.0002

Data Index: 861945 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0808. Min Act: -0.0002

Data Index: 701994 (C4 (Web Text))

Max Activating Token Index: 389

Text #17

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0814. Min Act: -0.0002

Data Index: 1265594 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0817. Min Act: -0.0002

Data Index: 829211 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 0.0993. Min Range: -0.0993

Max Act: 0.0823. Min Act: -0.0002

Data Index: 1588553 (Python Code)

Max Activating Token Index: 401