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

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

Neuron 5820 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: 5.8430. Min Range: -5.8430

Max Act: 5.8430. Min Act: -0.0000

Data Index: 12158 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 5.8430. Min Range: -5.8430

Max Act: 5.5304. Min Act: 0.0000

Data Index: 165555 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 5.8430. Min Range: -5.8430

Max Act: 5.2758. Min Act: -0.0000

Data Index: 1225229 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 5.8430. Min Range: -5.8430

Max Act: 5.1743. Min Act: -0.0000

Data Index: 853704 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 5.8430. Min Range: -5.8430

Max Act: 5.3397. Min Act: 0.0000

Data Index: 846391 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 5.8430. Min Range: -5.8430

Max Act: 5.4888. Min Act: -0.0000

Data Index: 1348541 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 5.8430. Min Range: -5.8430

Max Act: 5.0553. Min Act: 0.0001

Data Index: 1192994 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 5.8430. Min Range: -5.8430

Max Act: 4.7918. Min Act: -0.0000

Data Index: 532518 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 5.8430. Min Range: -5.8430

Max Act: 5.0028. Min Act: -0.0000

Data Index: 558484 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 5.8430. Min Range: -5.8430

Max Act: 4.9731. Min Act: -0.0000

Data Index: 921383 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 5.8430. Min Range: -5.8430

Max Act: 5.0503. Min Act: -0.0000

Data Index: 549686 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 5.8430. Min Range: -5.8430

Max Act: 4.8417. Min Act: -0.0000

Data Index: 736313 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 5.8430. Min Range: -5.8430

Max Act: 4.8446. Min Act: -0.0000

Data Index: 648998 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 5.8430. Min Range: -5.8430

Max Act: 4.4753. Min Act: -0.0000

Data Index: 536573 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 5.8430. Min Range: -5.8430

Max Act: 4.8068. Min Act: -0.0000

Data Index: 681464 (C4 (Web Text))

Max Activating Token Index: 843

Text #15

Max Range: 5.8430. Min Range: -5.8430

Max Act: 4.8031. Min Act: -0.0000

Data Index: 304566 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 5.8430. Min Range: -5.8430

Max Act: 4.8468. Min Act: -0.0000

Data Index: 920358 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 5.8430. Min Range: -5.8430

Max Act: 4.8335. Min Act: -0.0000

Data Index: 122081 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 5.8430. Min Range: -5.8430

Max Act: 4.5815. Min Act: -0.0000

Data Index: 808092 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 5.8430. Min Range: -5.8430

Max Act: 4.9914. Min Act: -0.0000

Data Index: 908203 (C4 (Web Text))

Max Activating Token Index: 181