Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3705 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.7528. Min Act: -0.0000

Data Index: 119528 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.6787. Min Act: -0.0000

Data Index: 659651 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.6520. Min Act: -0.0000

Data Index: 792463 (C4 (Web Text))

Max Activating Token Index: 511

Text #3

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.7197. Min Act: -0.0000

Data Index: 1109827 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.5208. Min Act: -0.0000

Data Index: 1335342 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.5786. Min Act: -0.0000

Data Index: 1202334 (C4 (Web Text))

Max Activating Token Index: 327

Text #6

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.5223. Min Act: -0.0000

Data Index: 137444 (C4 (Web Text))

Max Activating Token Index: 903

Text #7

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.5093. Min Act: -0.0000

Data Index: 848574 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.5048. Min Act: -0.0000

Data Index: 775902 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4936. Min Act: -0.0000

Data Index: 330732 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4824. Min Act: -0.0000

Data Index: 1344920 (C4 (Web Text))

Max Activating Token Index: 476

Text #11

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4650. Min Act: -0.0000

Data Index: 1350635 (C4 (Web Text))

Max Activating Token Index: 573

Text #12

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4554. Min Act: -0.0000

Data Index: 371595 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4667. Min Act: -0.0000

Data Index: 561773 (C4 (Web Text))

Max Activating Token Index: 653

Text #14

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4390. Min Act: -0.0000

Data Index: 391448 (C4 (Web Text))

Max Activating Token Index: 645

Text #15

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4480. Min Act: -0.0000

Data Index: 1215017 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4346. Min Act: -0.0000

Data Index: 637733 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4424. Min Act: -0.0000

Data Index: 1283309 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4501. Min Act: -0.0000

Data Index: 913062 (C4 (Web Text))

Max Activating Token Index: 962

Text #19

Max Range: 0.7528. Min Range: -0.7528

Max Act: 0.4570. Min Act: -0.0000

Data Index: 376599 (C4 (Web Text))

Max Activating Token Index: 390