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

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

Neuron 4052 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1713. Min Act: -0.0001

Data Index: 1002817 (C4 (Web Text))

Max Activating Token Index: 361

Text #1

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1547. Min Act: -0.0001

Data Index: 933301 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1664. Min Act: -0.0001

Data Index: 760245 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1860. Min Act: -0.0001

Data Index: 570474 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1731. Min Act: -0.0001

Data Index: 804937 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1596. Min Act: -0.0001

Data Index: 1201881 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1810. Min Act: -0.0001

Data Index: 706221 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1607. Min Act: -0.0001

Data Index: 1052474 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1752. Min Act: -0.0001

Data Index: 235594 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1705. Min Act: -0.0001

Data Index: 998259 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1493. Min Act: -0.0001

Data Index: 705895 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1463. Min Act: -0.0001

Data Index: 1114406 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1484. Min Act: -0.0001

Data Index: 955564 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1488. Min Act: -0.0001

Data Index: 819630 (C4 (Web Text))

Max Activating Token Index: 364

Text #14

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1468. Min Act: -0.0001

Data Index: 606363 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1456. Min Act: -0.0001

Data Index: 153218 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1474. Min Act: -0.0001

Data Index: 989550 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1404. Min Act: -0.0001

Data Index: 561072 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1607. Min Act: -0.0001

Data Index: 915610 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1838. Min Act: -0.0001

Data Index: 807425 (C4 (Web Text))

Max Activating Token Index: 209