Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 700 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0704. Min Act: -0.0001

Data Index: 1620099 (Python Code)

Max Activating Token Index: 221

Text #1

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0767. Min Act: -0.0001

Data Index: 1482106 (Python Code)

Max Activating Token Index: 130

Text #2

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0772. Min Act: -0.0001

Data Index: 219347 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0698. Min Act: -0.0001

Data Index: 293859 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0752. Min Act: -0.0001

Data Index: 301732 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0611. Min Act: -0.0001

Data Index: 321885 (C4 (Web Text))

Max Activating Token Index: 871

Text #6

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0670. Min Act: -0.0001

Data Index: 1547500 (Python Code)

Max Activating Token Index: 141

Text #7

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0697. Min Act: -0.0001

Data Index: 732972 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0671. Min Act: -0.0001

Data Index: 1395973 (Python Code)

Max Activating Token Index: 512

Text #9

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0673. Min Act: -0.0001

Data Index: 661085 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0647. Min Act: -0.0001

Data Index: 1463600 (Python Code)

Max Activating Token Index: 349

Text #11

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0573. Min Act: -0.0001

Data Index: 1380905 (Python Code)

Max Activating Token Index: 679

Text #12

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0593. Min Act: -0.0001

Data Index: 1532756 (Python Code)

Max Activating Token Index: 294

Text #13

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0577. Min Act: -0.0001

Data Index: 1597768 (Python Code)

Max Activating Token Index: 90

Text #14

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0590. Min Act: -0.0001

Data Index: 1485790 (Python Code)

Max Activating Token Index: 599

Text #15

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0608. Min Act: -0.0001

Data Index: 1181062 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0548. Min Act: -0.0001

Data Index: 1525668 (Python Code)

Max Activating Token Index: 810

Text #17

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0599. Min Act: -0.0001

Data Index: 352188 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0576. Min Act: -0.0001

Data Index: 1520470 (Python Code)

Max Activating Token Index: 475

Text #19

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0531. Min Act: -0.0001

Data Index: 1541087 (Python Code)

Max Activating Token Index: 112