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

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

Neuron 4156 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.8223. Min Act: -0.0000

Data Index: 1366489 (Python Code)

Max Activating Token Index: 957

Text #1

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.7068. Min Act: -0.0000

Data Index: 1413649 (Python Code)

Max Activating Token Index: 287

Text #2

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.6482. Min Act: -0.0000

Data Index: 1572786 (Python Code)

Max Activating Token Index: 935

Text #3

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.6555. Min Act: -0.0000

Data Index: 1620142 (Python Code)

Max Activating Token Index: 482

Text #4

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.6277. Min Act: -0.0000

Data Index: 1538521 (Python Code)

Max Activating Token Index: 459

Text #5

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.6610. Min Act: -0.0000

Data Index: 1390673 (Python Code)

Max Activating Token Index: 736

Text #6

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.6244. Min Act: -0.0000

Data Index: 927665 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.5932. Min Act: -0.0000

Data Index: 1496247 (Python Code)

Max Activating Token Index: 702

Text #8

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.5765. Min Act: -0.0000

Data Index: 1446808 (Python Code)

Max Activating Token Index: 573

Text #9

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.5043. Min Act: -0.0000

Data Index: 1616736 (Python Code)

Max Activating Token Index: 789

Text #10

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.5840. Min Act: -0.0000

Data Index: 715453 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.5579. Min Act: -0.0000

Data Index: 1451519 (Python Code)

Max Activating Token Index: 583

Text #12

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.5413. Min Act: -0.0000

Data Index: 641940 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.5427. Min Act: -0.0000

Data Index: 260982 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.5120. Min Act: -0.0000

Data Index: 1383743 (Python Code)

Max Activating Token Index: 75

Text #15

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.5262. Min Act: -0.0000

Data Index: 1619650 (Python Code)

Max Activating Token Index: 378

Text #16

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.5704. Min Act: -0.0000

Data Index: 1430763 (Python Code)

Max Activating Token Index: 742

Text #17

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.5311. Min Act: -0.0000

Data Index: 1550644 (Python Code)

Max Activating Token Index: 521

Text #18

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.5507. Min Act: -0.0000

Data Index: 1625742 (Python Code)

Max Activating Token Index: 532

Text #19

Max Range: 0.8223. Min Range: -0.8223

Max Act: 0.5305. Min Act: -0.0000

Data Index: 630149 (C4 (Web Text))

Max Activating Token Index: 305