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

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

Neuron 3706 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0606. Min Act: -0.0002

Data Index: 3860 (C4 (Web Text))

Max Activating Token Index: 592

Text #1

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0526. Min Act: -0.0002

Data Index: 686954 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0521. Min Act: -0.0002

Data Index: 720476 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0510. Min Act: -0.0002

Data Index: 180937 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0472. Min Act: -0.0002

Data Index: 1011975 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0494. Min Act: -0.0002

Data Index: 678268 (C4 (Web Text))

Max Activating Token Index: 589

Text #6

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0503. Min Act: -0.0002

Data Index: 286683 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0478. Min Act: -0.0002

Data Index: 487169 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0466. Min Act: -0.0002

Data Index: 639106 (C4 (Web Text))

Max Activating Token Index: 564

Text #9

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0515. Min Act: -0.0002

Data Index: 214588 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0494. Min Act: -0.0002

Data Index: 640147 (C4 (Web Text))

Max Activating Token Index: 953

Text #11

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0459. Min Act: -0.0002

Data Index: 635141 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0459. Min Act: -0.0002

Data Index: 1242886 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0476. Min Act: -0.0002

Data Index: 624358 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0452. Min Act: -0.0002

Data Index: 957212 (C4 (Web Text))

Max Activating Token Index: 176

Text #15

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0471. Min Act: -0.0002

Data Index: 1348770 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0449. Min Act: -0.0002

Data Index: 113258 (C4 (Web Text))

Max Activating Token Index: 955

Text #17

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0461. Min Act: -0.0002

Data Index: 446392 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0441. Min Act: -0.0002

Data Index: 548127 (C4 (Web Text))

Max Activating Token Index: 580

Text #19

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0427. Min Act: -0.0002

Data Index: 1087590 (C4 (Web Text))

Max Activating Token Index: 183