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

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

Neuron 1358 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7425. Min Range: -3.7425

Max Act: 3.7425. Min Act: -0.0001

Data Index: 43232 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 3.7425. Min Range: -3.7425

Max Act: 3.2038. Min Act: -0.0001

Data Index: 326541 (C4 (Web Text))

Max Activating Token Index: 863

Text #2

Max Range: 3.7425. Min Range: -3.7425

Max Act: 2.8488. Min Act: -0.0001

Data Index: 707206 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 3.7425. Min Range: -3.7425

Max Act: 2.9376. Min Act: -0.0000

Data Index: 709260 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 3.7425. Min Range: -3.7425

Max Act: 2.8760. Min Act: -0.0001

Data Index: 1152653 (C4 (Web Text))

Max Activating Token Index: 189

Text #5

Max Range: 3.7425. Min Range: -3.7425

Max Act: 2.7601. Min Act: -0.0001

Data Index: 301416 (C4 (Web Text))

Max Activating Token Index: 412

Text #6

Max Range: 3.7425. Min Range: -3.7425

Max Act: 3.0066. Min Act: -0.0001

Data Index: 272094 (C4 (Web Text))

Max Activating Token Index: 982

Text #7

Max Range: 3.7425. Min Range: -3.7425

Max Act: 2.7514. Min Act: -0.0001

Data Index: 561694 (C4 (Web Text))

Max Activating Token Index: 691

Text #8

Max Range: 3.7425. Min Range: -3.7425

Max Act: 3.0355. Min Act: -0.0001

Data Index: 21784 (C4 (Web Text))

Max Activating Token Index: 599

Text #9

Max Range: 3.7425. Min Range: -3.7425

Max Act: 2.8850. Min Act: -0.0001

Data Index: 1162298 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 3.7425. Min Range: -3.7425

Max Act: 2.8859. Min Act: -0.0001

Data Index: 978695 (C4 (Web Text))

Max Activating Token Index: 634

Text #11

Max Range: 3.7425. Min Range: -3.7425

Max Act: 3.0080. Min Act: -0.0001

Data Index: 1267974 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 3.7425. Min Range: -3.7425

Max Act: 2.6883. Min Act: -0.0001

Data Index: 1099943 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 3.7425. Min Range: -3.7425

Max Act: 2.9681. Min Act: -0.0001

Data Index: 244425 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 3.7425. Min Range: -3.7425

Max Act: 2.9272. Min Act: -0.0001

Data Index: 861382 (C4 (Web Text))

Max Activating Token Index: 839

Text #15

Max Range: 3.7425. Min Range: -3.7425

Max Act: 2.7870. Min Act: -0.0001

Data Index: 677971 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 3.7425. Min Range: -3.7425

Max Act: 2.7558. Min Act: -0.0001

Data Index: 774985 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 3.7425. Min Range: -3.7425

Max Act: 2.8088. Min Act: -0.0001

Data Index: 18957 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 3.7425. Min Range: -3.7425

Max Act: 2.7544. Min Act: -0.0001

Data Index: 56246 (C4 (Web Text))

Max Activating Token Index: 498

Text #19

Max Range: 3.7425. Min Range: -3.7425

Max Act: 3.0210. Min Act: -0.0001

Data Index: 278216 (C4 (Web Text))

Max Activating Token Index: 113