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

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

Neuron 3564 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.3430. Min Act: -0.0001

Data Index: 330764 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.3120. Min Act: -0.0000

Data Index: 1307628 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.3256. Min Act: -0.0000

Data Index: 1355318 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.3286. Min Act: -0.0001

Data Index: 1297504 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2706. Min Act: -0.0000

Data Index: 1332382 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2571. Min Act: -0.0000

Data Index: 8903 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2609. Min Act: -0.0000

Data Index: 737688 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2867. Min Act: -0.0000

Data Index: 768570 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2549. Min Act: -0.0000

Data Index: 528315 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2567. Min Act: -0.0000

Data Index: 1219454 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2151. Min Act: -0.0000

Data Index: 1051126 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2373. Min Act: -0.0000

Data Index: 1276380 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2278. Min Act: -0.0001

Data Index: 781012 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2204. Min Act: -0.0000

Data Index: 575868 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2243. Min Act: -0.0000

Data Index: 838843 (C4 (Web Text))

Max Activating Token Index: 151

Text #15

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2237. Min Act: -0.0000

Data Index: 708278 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2315. Min Act: -0.0000

Data Index: 66395 (C4 (Web Text))

Max Activating Token Index: 461

Text #17

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2303. Min Act: -0.0000

Data Index: 760867 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2061. Min Act: -0.0000

Data Index: 321392 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 0.3430. Min Range: -0.3430

Max Act: 0.2204. Min Act: -0.0000

Data Index: 855330 (C4 (Web Text))

Max Activating Token Index: 355