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

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

Neuron 4539 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9757. Min Range: -2.9757

Max Act: 2.9757. Min Act: -0.0000

Data Index: 909395 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 2.9757. Min Range: -2.9757

Max Act: 2.7178. Min Act: -0.0000

Data Index: 596325 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 2.9757. Min Range: -2.9757

Max Act: 2.9724. Min Act: -0.0000

Data Index: 770119 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 2.9757. Min Range: -2.9757

Max Act: 2.8602. Min Act: -0.0000

Data Index: 773067 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 2.9757. Min Range: -2.9757

Max Act: 2.5419. Min Act: -0.0000

Data Index: 598982 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 2.9757. Min Range: -2.9757

Max Act: 2.6683. Min Act: -0.0000

Data Index: 198682 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 2.9757. Min Range: -2.9757

Max Act: 2.7512. Min Act: -0.0000

Data Index: 604312 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 2.9757. Min Range: -2.9757

Max Act: 2.4591. Min Act: -0.0000

Data Index: 1280636 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 2.9757. Min Range: -2.9757

Max Act: 2.6538. Min Act: -0.0000

Data Index: 228047 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 2.9757. Min Range: -2.9757

Max Act: 2.5395. Min Act: -0.0000

Data Index: 566864 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 2.9757. Min Range: -2.9757

Max Act: 2.2548. Min Act: -0.0000

Data Index: 1016766 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 2.9757. Min Range: -2.9757

Max Act: 2.4328. Min Act: -0.0000

Data Index: 784702 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 2.9757. Min Range: -2.9757

Max Act: 2.5267. Min Act: -0.0000

Data Index: 676977 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 2.9757. Min Range: -2.9757

Max Act: 2.4691. Min Act: -0.0000

Data Index: 445681 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 2.9757. Min Range: -2.9757

Max Act: 2.4717. Min Act: -0.0000

Data Index: 375821 (C4 (Web Text))

Max Activating Token Index: 592

Text #15

Max Range: 2.9757. Min Range: -2.9757

Max Act: 2.3772. Min Act: -0.0000

Data Index: 387167 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 2.9757. Min Range: -2.9757

Max Act: 1.9251. Min Act: -0.0000

Data Index: 1134305 (C4 (Web Text))

Max Activating Token Index: 192

Text #17

Max Range: 2.9757. Min Range: -2.9757

Max Act: 2.2420. Min Act: -0.0000

Data Index: 37573 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 2.9757. Min Range: -2.9757

Max Act: 2.2512. Min Act: -0.0000

Data Index: 828207 (C4 (Web Text))

Max Activating Token Index: 957

Text #19

Max Range: 2.9757. Min Range: -2.9757

Max Act: 2.0855. Min Act: -0.0000

Data Index: 1052654 (C4 (Web Text))

Max Activating Token Index: 511