Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1049 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1514. Min Act: -0.0001

Data Index: 350222 (C4 (Web Text))

Max Activating Token Index: 517

Text #1

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1649. Min Act: -0.0001

Data Index: 482927 (C4 (Web Text))

Max Activating Token Index: 859

Text #2

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1502. Min Act: -0.0002

Data Index: 469016 (C4 (Web Text))

Max Activating Token Index: 486

Text #3

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1629. Min Act: -0.0002

Data Index: 842052 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1570. Min Act: -0.0001

Data Index: 10837 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1432. Min Act: -0.0001

Data Index: 498650 (C4 (Web Text))

Max Activating Token Index: 68

Text #6

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1381. Min Act: -0.0001

Data Index: 185296 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1368. Min Act: -0.0001

Data Index: 164740 (C4 (Web Text))

Max Activating Token Index: 714

Text #8

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1220. Min Act: -0.0001

Data Index: 723469 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1451. Min Act: -0.0001

Data Index: 512837 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1308. Min Act: -0.0001

Data Index: 451065 (C4 (Web Text))

Max Activating Token Index: 623

Text #11

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1398. Min Act: -0.0001

Data Index: 1238850 (C4 (Web Text))

Max Activating Token Index: 462

Text #12

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1371. Min Act: -0.0001

Data Index: 418851 (C4 (Web Text))

Max Activating Token Index: 660

Text #13

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1453. Min Act: -0.0001

Data Index: 1091712 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1549. Min Act: -0.0002

Data Index: 1229558 (C4 (Web Text))

Max Activating Token Index: 983

Text #15

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1365. Min Act: -0.0002

Data Index: 1321037 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1315. Min Act: -0.0001

Data Index: 138037 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1326. Min Act: -0.0001

Data Index: 163759 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1262. Min Act: -0.0002

Data Index: 884535 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1199. Min Act: -0.0001

Data Index: 1165894 (C4 (Web Text))

Max Activating Token Index: 880