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

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

Neuron 1791 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0517. Min Act: -0.0003

Data Index: 957093 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0526. Min Act: -0.0003

Data Index: 1262543 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0506. Min Act: -0.0003

Data Index: 908488 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0478. Min Act: -0.0003

Data Index: 1246064 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0512. Min Act: -0.0003

Data Index: 438383 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0495. Min Act: -0.0003

Data Index: 487411 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0513. Min Act: -0.0003

Data Index: 14379 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0479. Min Act: -0.0003

Data Index: 1325417 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0503. Min Act: -0.0003

Data Index: 870152 (C4 (Web Text))

Max Activating Token Index: 963

Text #9

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0479. Min Act: -0.0003

Data Index: 1234309 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0489. Min Act: -0.0003

Data Index: 1018397 (C4 (Web Text))

Max Activating Token Index: 606

Text #11

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0457. Min Act: -0.0003

Data Index: 1055568 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0466. Min Act: -0.0003

Data Index: 996893 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0481. Min Act: -0.0003

Data Index: 464514 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0500. Min Act: -0.0003

Data Index: 769994 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0454. Min Act: -0.0003

Data Index: 171497 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0463. Min Act: -0.0003

Data Index: 775609 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0451. Min Act: -0.0003

Data Index: 987667 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0443. Min Act: -0.0003

Data Index: 890125 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0454. Min Act: -0.0003

Data Index: 104840 (C4 (Web Text))

Max Activating Token Index: 854