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

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

Neuron 1989 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0326. Min Range: -4.0326

Max Act: 3.5815. Min Act: -0.0000

Data Index: 1499080 (Python Code)

Max Activating Token Index: 416

Text #1

Max Range: 4.0326. Min Range: -4.0326

Max Act: 4.0326. Min Act: -0.0000

Data Index: 1612446 (Python Code)

Max Activating Token Index: 726

Text #2

Max Range: 4.0326. Min Range: -4.0326

Max Act: 3.6708. Min Act: -0.0000

Data Index: 1559916 (Python Code)

Max Activating Token Index: 562

Text #3

Max Range: 4.0326. Min Range: -4.0326

Max Act: 3.6251. Min Act: -0.0000

Data Index: 1414371 (Python Code)

Max Activating Token Index: 852

Text #4

Max Range: 4.0326. Min Range: -4.0326

Max Act: 3.3386. Min Act: -0.0000

Data Index: 1384044 (Python Code)

Max Activating Token Index: 807

Text #5

Max Range: 4.0326. Min Range: -4.0326

Max Act: 3.3296. Min Act: -0.0000

Data Index: 1585743 (Python Code)

Max Activating Token Index: 571

Text #6

Max Range: 4.0326. Min Range: -4.0326

Max Act: 3.5236. Min Act: -0.0000

Data Index: 1629840 (Python Code)

Max Activating Token Index: 504

Text #7

Max Range: 4.0326. Min Range: -4.0326

Max Act: 3.1870. Min Act: -0.0000

Data Index: 1371967 (Python Code)

Max Activating Token Index: 947

Text #8

Max Range: 4.0326. Min Range: -4.0326

Max Act: 3.1668. Min Act: -0.0000

Data Index: 542622 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 4.0326. Min Range: -4.0326

Max Act: 3.3254. Min Act: -0.0000

Data Index: 1561589 (Python Code)

Max Activating Token Index: 505

Text #10

Max Range: 4.0326. Min Range: -4.0326

Max Act: 3.5657. Min Act: -0.0000

Data Index: 1595204 (Python Code)

Max Activating Token Index: 1004

Text #11

Max Range: 4.0326. Min Range: -4.0326

Max Act: 3.2481. Min Act: -0.0000

Data Index: 1480191 (Python Code)

Max Activating Token Index: 771

Text #12

Max Range: 4.0326. Min Range: -4.0326

Max Act: 3.2453. Min Act: -0.0000

Data Index: 1504956 (Python Code)

Max Activating Token Index: 359

Text #13

Max Range: 4.0326. Min Range: -4.0326

Max Act: 3.5644. Min Act: -0.0000

Data Index: 1640462 (Python Code)

Max Activating Token Index: 666

Text #14

Max Range: 4.0326. Min Range: -4.0326

Max Act: 2.9771. Min Act: -0.0000

Data Index: 1433713 (Python Code)

Max Activating Token Index: 892

Text #15

Max Range: 4.0326. Min Range: -4.0326

Max Act: 3.1780. Min Act: -0.0000

Data Index: 1375132 (Python Code)

Max Activating Token Index: 930

Text #16

Max Range: 4.0326. Min Range: -4.0326

Max Act: 3.1262. Min Act: -0.0000

Data Index: 1447730 (Python Code)

Max Activating Token Index: 910

Text #17

Max Range: 4.0326. Min Range: -4.0326

Max Act: 3.0936. Min Act: -0.0000

Data Index: 1642732 (Python Code)

Max Activating Token Index: 102

Text #18

Max Range: 4.0326. Min Range: -4.0326

Max Act: 2.9334. Min Act: -0.0000

Data Index: 1647030 (Python Code)

Max Activating Token Index: 929

Text #19

Max Range: 4.0326. Min Range: -4.0326

Max Act: 3.0790. Min Act: -0.0000

Data Index: 1563388 (Python Code)

Max Activating Token Index: 458