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

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

Neuron 672 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: 2.1427. Min Range: -2.1427

Max Act: 2.1427. Min Act: -0.0000

Data Index: 527557 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 2.1427. Min Range: -2.1427

Max Act: 1.9041. Min Act: -0.0000

Data Index: 185501 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 2.1427. Min Range: -2.1427

Max Act: 1.7870. Min Act: -0.0000

Data Index: 526460 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 2.1427. Min Range: -2.1427

Max Act: 1.7050. Min Act: -0.0000

Data Index: 106665 (C4 (Web Text))

Max Activating Token Index: 513

Text #4

Max Range: 2.1427. Min Range: -2.1427

Max Act: 1.7525. Min Act: -0.0000

Data Index: 690833 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 2.1427. Min Range: -2.1427

Max Act: 1.5331. Min Act: -0.0000

Data Index: 1033623 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 2.1427. Min Range: -2.1427

Max Act: 1.5765. Min Act: -0.0000

Data Index: 1323655 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 2.1427. Min Range: -2.1427

Max Act: 1.6613. Min Act: -0.0000

Data Index: 865237 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 2.1427. Min Range: -2.1427

Max Act: 1.5572. Min Act: -0.0000

Data Index: 307243 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 2.1427. Min Range: -2.1427

Max Act: 1.4621. Min Act: -0.0000

Data Index: 507603 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 2.1427. Min Range: -2.1427

Max Act: 1.5159. Min Act: -0.0000

Data Index: 13008 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 2.1427. Min Range: -2.1427

Max Act: 1.3907. Min Act: -0.0000

Data Index: 589891 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 2.1427. Min Range: -2.1427

Max Act: 1.4539. Min Act: -0.0000

Data Index: 488851 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 2.1427. Min Range: -2.1427

Max Act: 1.4602. Min Act: -0.0000

Data Index: 241823 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 2.1427. Min Range: -2.1427

Max Act: 1.5348. Min Act: -0.0000

Data Index: 1084524 (C4 (Web Text))

Max Activating Token Index: 328

Text #15

Max Range: 2.1427. Min Range: -2.1427

Max Act: 1.3553. Min Act: -0.0000

Data Index: 390127 (C4 (Web Text))

Max Activating Token Index: 721

Text #16

Max Range: 2.1427. Min Range: -2.1427

Max Act: 1.3878. Min Act: -0.0000

Data Index: 618312 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 2.1427. Min Range: -2.1427

Max Act: 1.3419. Min Act: -0.0000

Data Index: 430417 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 2.1427. Min Range: -2.1427

Max Act: 1.2129. Min Act: -0.0000

Data Index: 599530 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 2.1427. Min Range: -2.1427

Max Act: 1.2140. Min Act: -0.0000

Data Index: 526847 (C4 (Web Text))

Max Activating Token Index: 508