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

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

Neuron 2531 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2132. Min Range: -0.2132

Max Act: 0.2132. Min Act: -0.0000

Data Index: 77915 (C4 (Web Text))

Max Activating Token Index: 313

Text #1

Max Range: 0.2132. Min Range: -0.2132

Max Act: 0.1760. Min Act: -0.0000

Data Index: 1014526 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 0.2132. Min Range: -0.2132

Max Act: 0.1681. Min Act: -0.0000

Data Index: 1003765 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 0.2132. Min Range: -0.2132

Max Act: 0.1539. Min Act: -0.0000

Data Index: 441522 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 0.2132. Min Range: -0.2132

Max Act: 0.1628. Min Act: -0.0000

Data Index: 38267 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 0.2132. Min Range: -0.2132

Max Act: 0.1603. Min Act: -0.0000

Data Index: 618635 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 0.2132. Min Range: -0.2132

Max Act: 0.1580. Min Act: -0.0000

Data Index: 454850 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 0.2132. Min Range: -0.2132

Max Act: 0.1554. Min Act: -0.0001

Data Index: 857515 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 0.2132. Min Range: -0.2132

Max Act: 0.1524. Min Act: -0.0000

Data Index: 468150 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 0.2132. Min Range: -0.2132

Max Act: 0.1521. Min Act: -0.0000

Data Index: 1135398 (C4 (Web Text))

Max Activating Token Index: 538

Text #10

Max Range: 0.2132. Min Range: -0.2132

Max Act: 0.1512. Min Act: -0.0000

Data Index: 970666 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 0.2132. Min Range: -0.2132

Max Act: 0.1425. Min Act: -0.0000

Data Index: 568389 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 0.2132. Min Range: -0.2132

Max Act: 0.1550. Min Act: -0.0000

Data Index: 493575 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 0.2132. Min Range: -0.2132

Max Act: 0.1396. Min Act: -0.0000

Data Index: 202582 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 0.2132. Min Range: -0.2132

Max Act: 0.1482. Min Act: -0.0000

Data Index: 345652 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 0.2132. Min Range: -0.2132

Max Act: 0.1503. Min Act: -0.0000

Data Index: 517281 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 0.2132. Min Range: -0.2132

Max Act: 0.1406. Min Act: -0.0000

Data Index: 886038 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 0.2132. Min Range: -0.2132

Max Act: 0.1446. Min Act: -0.0001

Data Index: 597733 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 0.2132. Min Range: -0.2132

Max Act: 0.1377. Min Act: -0.0001

Data Index: 172639 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 0.2132. Min Range: -0.2132

Max Act: 0.1354. Min Act: -0.0000

Data Index: 546763 (C4 (Web Text))

Max Activating Token Index: 963