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

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

Neuron 2480 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3394. Min Range: -1.3394

Max Act: 1.3389. Min Act: -0.0000

Data Index: 632171 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 1.3394. Min Range: -1.3394

Max Act: 1.3394. Min Act: -0.0000

Data Index: 845526 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 1.3394. Min Range: -1.3394

Max Act: 0.9716. Min Act: -0.0001

Data Index: 367825 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 1.3394. Min Range: -1.3394

Max Act: 1.1547. Min Act: -0.0000

Data Index: 1318420 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 1.3394. Min Range: -1.3394

Max Act: 1.1451. Min Act: -0.0000

Data Index: 1129051 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 1.3394. Min Range: -1.3394

Max Act: 1.1266. Min Act: -0.0000

Data Index: 713959 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 1.3394. Min Range: -1.3394

Max Act: 1.0942. Min Act: -0.0000

Data Index: 411675 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 1.3394. Min Range: -1.3394

Max Act: 1.1603. Min Act: -0.0001

Data Index: 708087 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 1.3394. Min Range: -1.3394

Max Act: 1.0481. Min Act: -0.0001

Data Index: 441274 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 1.3394. Min Range: -1.3394

Max Act: 1.0624. Min Act: -0.0000

Data Index: 1344557 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 1.3394. Min Range: -1.3394

Max Act: 0.9586. Min Act: -0.0000

Data Index: 890812 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 1.3394. Min Range: -1.3394

Max Act: 1.0558. Min Act: -0.0000

Data Index: 56091 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 1.3394. Min Range: -1.3394

Max Act: 1.1399. Min Act: -0.0000

Data Index: 549096 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 1.3394. Min Range: -1.3394

Max Act: 1.0064. Min Act: -0.0001

Data Index: 1070475 (C4 (Web Text))

Max Activating Token Index: 815

Text #14

Max Range: 1.3394. Min Range: -1.3394

Max Act: 1.0357. Min Act: -0.0001

Data Index: 476383 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 1.3394. Min Range: -1.3394

Max Act: 1.0735. Min Act: -0.0000

Data Index: 1305903 (C4 (Web Text))

Max Activating Token Index: 634

Text #16

Max Range: 1.3394. Min Range: -1.3394

Max Act: 1.0443. Min Act: -0.0001

Data Index: 88661 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 1.3394. Min Range: -1.3394

Max Act: 0.9447. Min Act: -0.0001

Data Index: 1208208 (C4 (Web Text))

Max Activating Token Index: 616

Text #18

Max Range: 1.3394. Min Range: -1.3394

Max Act: 0.9950. Min Act: -0.0000

Data Index: 331852 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 1.3394. Min Range: -1.3394

Max Act: 0.9534. Min Act: -0.0000

Data Index: 826597 (C4 (Web Text))

Max Activating Token Index: 531