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

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

Neuron 825 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2967. Min Range: -4.2967

Max Act: 4.2967. Min Act: -0.0001

Data Index: 304030 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 4.2967. Min Range: -4.2967

Max Act: 3.7401. Min Act: -0.0001

Data Index: 96392 (C4 (Web Text))

Max Activating Token Index: 692

Text #2

Max Range: 4.2967. Min Range: -4.2967

Max Act: 3.5744. Min Act: -0.0001

Data Index: 1548737 (Python Code)

Max Activating Token Index: 261

Text #3

Max Range: 4.2967. Min Range: -4.2967

Max Act: 3.4317. Min Act: -0.0001

Data Index: 145371 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 4.2967. Min Range: -4.2967

Max Act: 3.3845. Min Act: -0.0001

Data Index: 208780 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 4.2967. Min Range: -4.2967

Max Act: 3.3733. Min Act: -0.0001

Data Index: 255561 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 4.2967. Min Range: -4.2967

Max Act: 3.3361. Min Act: -0.0001

Data Index: 611724 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 4.2967. Min Range: -4.2967

Max Act: 3.3031. Min Act: -0.0001

Data Index: 825212 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 4.2967. Min Range: -4.2967

Max Act: 3.2605. Min Act: -0.0001

Data Index: 244139 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 4.2967. Min Range: -4.2967

Max Act: 3.3178. Min Act: -0.0001

Data Index: 934101 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 4.2967. Min Range: -4.2967

Max Act: 2.8754. Min Act: -0.0001

Data Index: 675276 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 4.2967. Min Range: -4.2967

Max Act: 3.1330. Min Act: -0.0001

Data Index: 890616 (C4 (Web Text))

Max Activating Token Index: 393

Text #12

Max Range: 4.2967. Min Range: -4.2967

Max Act: 3.1600. Min Act: -0.0001

Data Index: 13956 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 4.2967. Min Range: -4.2967

Max Act: 3.0964. Min Act: -0.0001

Data Index: 1637798 (Python Code)

Max Activating Token Index: 412

Text #14

Max Range: 4.2967. Min Range: -4.2967

Max Act: 3.0938. Min Act: -0.0001

Data Index: 1307733 (C4 (Web Text))

Max Activating Token Index: 547

Text #15

Max Range: 4.2967. Min Range: -4.2967

Max Act: 3.0445. Min Act: -0.0001

Data Index: 1307864 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 4.2967. Min Range: -4.2967

Max Act: 3.0372. Min Act: -0.0001

Data Index: 488002 (C4 (Web Text))

Max Activating Token Index: 941

Text #17

Max Range: 4.2967. Min Range: -4.2967

Max Act: 3.0319. Min Act: -0.0001

Data Index: 1655783 (Python Code)

Max Activating Token Index: 1022

Text #18

Max Range: 4.2967. Min Range: -4.2967

Max Act: 3.1662. Min Act: -0.0001

Data Index: 979631 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 4.2967. Min Range: -4.2967

Max Act: 2.9047. Min Act: -0.0001

Data Index: 291540 (C4 (Web Text))

Max Activating Token Index: 666