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

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

Neuron 3783 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1825. Min Act: -0.0001

Data Index: 447558 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1594. Min Act: -0.0002

Data Index: 111083 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1557. Min Act: -0.0002

Data Index: 379564 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1689. Min Act: -0.0001

Data Index: 360176 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1569. Min Act: -0.0002

Data Index: 1105804 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1557. Min Act: -0.0002

Data Index: 209808 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1395. Min Act: -0.0002

Data Index: 1162225 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1638. Min Act: -0.0002

Data Index: 16925 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1586. Min Act: -0.0002

Data Index: 1339789 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1636. Min Act: -0.0002

Data Index: 352543 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1575. Min Act: -0.0002

Data Index: 1260498 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1630. Min Act: -0.0001

Data Index: 137725 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1507. Min Act: -0.0001

Data Index: 1183103 (C4 (Web Text))

Max Activating Token Index: 413

Text #13

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1556. Min Act: -0.0001

Data Index: 935845 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1493. Min Act: -0.0001

Data Index: 290886 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1491. Min Act: -0.0002

Data Index: 607606 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1476. Min Act: -0.0002

Data Index: 1357958 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1639. Min Act: -0.0002

Data Index: 1316847 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1593. Min Act: -0.0002

Data Index: 1245110 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1545. Min Act: -0.0002

Data Index: 1338544 (C4 (Web Text))

Max Activating Token Index: 6