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

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

Neuron 5576 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: 6.4558. Min Range: -6.4558

Max Act: 6.4558. Min Act: -0.0000

Data Index: 627610 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 6.4558. Min Range: -6.4558

Max Act: 6.2443. Min Act: -0.0000

Data Index: 1277554 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 6.4558. Min Range: -6.4558

Max Act: 6.2695. Min Act: -0.0000

Data Index: 1351030 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 6.4558. Min Range: -6.4558

Max Act: 5.8883. Min Act: -0.0000

Data Index: 902731 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 6.4558. Min Range: -6.4558

Max Act: 5.6516. Min Act: -0.0000

Data Index: 279799 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 6.4558. Min Range: -6.4558

Max Act: 5.8870. Min Act: -0.0000

Data Index: 859893 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 6.4558. Min Range: -6.4558

Max Act: 5.4502. Min Act: -0.0000

Data Index: 397560 (C4 (Web Text))

Max Activating Token Index: 1003

Text #7

Max Range: 6.4558. Min Range: -6.4558

Max Act: 5.9549. Min Act: -0.0000

Data Index: 1246692 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 6.4558. Min Range: -6.4558

Max Act: 5.6494. Min Act: -0.0000

Data Index: 1200723 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 6.4558. Min Range: -6.4558

Max Act: 5.4430. Min Act: -0.0000

Data Index: 92361 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 6.4558. Min Range: -6.4558

Max Act: 5.4407. Min Act: -0.0000

Data Index: 956000 (C4 (Web Text))

Max Activating Token Index: 257

Text #11

Max Range: 6.4558. Min Range: -6.4558

Max Act: 5.4106. Min Act: -0.0000

Data Index: 1162229 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 6.4558. Min Range: -6.4558

Max Act: 5.3655. Min Act: -0.0000

Data Index: 299140 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 6.4558. Min Range: -6.4558

Max Act: 5.3282. Min Act: -0.0000

Data Index: 527077 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 6.4558. Min Range: -6.4558

Max Act: 5.1108. Min Act: -0.0000

Data Index: 882789 (C4 (Web Text))

Max Activating Token Index: 960

Text #15

Max Range: 6.4558. Min Range: -6.4558

Max Act: 5.1158. Min Act: -0.0000

Data Index: 238924 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 6.4558. Min Range: -6.4558

Max Act: 5.2473. Min Act: -0.0000

Data Index: 1248303 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 6.4558. Min Range: -6.4558

Max Act: 4.9653. Min Act: -0.0000

Data Index: 747992 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 6.4558. Min Range: -6.4558

Max Act: 4.9634. Min Act: -0.0000

Data Index: 1341068 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 6.4558. Min Range: -6.4558

Max Act: 4.9236. Min Act: -0.0000

Data Index: 1042939 (C4 (Web Text))

Max Activating Token Index: 168