Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4034 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1711. Min Act: -0.0000

Data Index: 613965 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1582. Min Act: -0.0000

Data Index: 399029 (C4 (Web Text))

Max Activating Token Index: 659

Text #2

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1752. Min Act: -0.0000

Data Index: 1351119 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1684. Min Act: -0.0000

Data Index: 469814 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1723. Min Act: -0.0000

Data Index: 543768 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1547. Min Act: -0.0000

Data Index: 468526 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1629. Min Act: -0.0000

Data Index: 425694 (C4 (Web Text))

Max Activating Token Index: 843

Text #7

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1636. Min Act: -0.0000

Data Index: 1271592 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1640. Min Act: -0.0000

Data Index: 1035991 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1567. Min Act: -0.0000

Data Index: 446440 (C4 (Web Text))

Max Activating Token Index: 365

Text #10

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1551. Min Act: -0.0000

Data Index: 260657 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1443. Min Act: -0.0000

Data Index: 567344 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1573. Min Act: -0.0000

Data Index: 154212 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1462. Min Act: -0.0000

Data Index: 202725 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1559. Min Act: -0.0000

Data Index: 531631 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1410. Min Act: -0.0000

Data Index: 1113701 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1523. Min Act: -0.0000

Data Index: 44714 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1595. Min Act: -0.0000

Data Index: 952592 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1484. Min Act: -0.0000

Data Index: 349882 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 0.1752. Min Range: -0.1752

Max Act: 0.1411. Min Act: -0.0000

Data Index: 92434 (C4 (Web Text))

Max Activating Token Index: 990