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

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

Neuron 3409 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0386. Min Range: -3.0386

Max Act: 3.0386. Min Act: -0.0000

Data Index: 1538944 (Python Code)

Max Activating Token Index: 756

Text #1

Max Range: 3.0386. Min Range: -3.0386

Max Act: 2.7690. Min Act: -0.0000

Data Index: 1367869 (Python Code)

Max Activating Token Index: 830

Text #2

Max Range: 3.0386. Min Range: -3.0386

Max Act: 2.5202. Min Act: -0.0000

Data Index: 1535820 (Python Code)

Max Activating Token Index: 171

Text #3

Max Range: 3.0386. Min Range: -3.0386

Max Act: 2.5768. Min Act: -0.0000

Data Index: 1409964 (Python Code)

Max Activating Token Index: 82

Text #4

Max Range: 3.0386. Min Range: -3.0386

Max Act: 2.3603. Min Act: -0.0000

Data Index: 1649874 (Python Code)

Max Activating Token Index: 112

Text #5

Max Range: 3.0386. Min Range: -3.0386

Max Act: 2.3540. Min Act: -0.0000

Data Index: 1559952 (Python Code)

Max Activating Token Index: 65

Text #6

Max Range: 3.0386. Min Range: -3.0386

Max Act: 2.2412. Min Act: -0.0000

Data Index: 1468877 (Python Code)

Max Activating Token Index: 40

Text #7

Max Range: 3.0386. Min Range: -3.0386

Max Act: 2.1210. Min Act: -0.0000

Data Index: 1637167 (Python Code)

Max Activating Token Index: 353

Text #8

Max Range: 3.0386. Min Range: -3.0386

Max Act: 2.1125. Min Act: -0.0000

Data Index: 1474501 (Python Code)

Max Activating Token Index: 312

Text #9

Max Range: 3.0386. Min Range: -3.0386

Max Act: 2.2155. Min Act: -0.0000

Data Index: 1380924 (Python Code)

Max Activating Token Index: 800

Text #10

Max Range: 3.0386. Min Range: -3.0386

Max Act: 2.2228. Min Act: -0.0000

Data Index: 1418999 (Python Code)

Max Activating Token Index: 479

Text #11

Max Range: 3.0386. Min Range: -3.0386

Max Act: 2.3206. Min Act: -0.0000

Data Index: 1386827 (Python Code)

Max Activating Token Index: 94

Text #12

Max Range: 3.0386. Min Range: -3.0386

Max Act: 2.0837. Min Act: -0.0000

Data Index: 1624761 (Python Code)

Max Activating Token Index: 653

Text #13

Max Range: 3.0386. Min Range: -3.0386

Max Act: 2.1231. Min Act: -0.0000

Data Index: 1656028 (Python Code)

Max Activating Token Index: 699

Text #14

Max Range: 3.0386. Min Range: -3.0386

Max Act: 2.2278. Min Act: -0.0000

Data Index: 1360346 (Python Code)

Max Activating Token Index: 546

Text #15

Max Range: 3.0386. Min Range: -3.0386

Max Act: 2.1174. Min Act: -0.0000

Data Index: 1634701 (Python Code)

Max Activating Token Index: 77

Text #16

Max Range: 3.0386. Min Range: -3.0386

Max Act: 2.2026. Min Act: -0.0000

Data Index: 1595686 (Python Code)

Max Activating Token Index: 572

Text #17

Max Range: 3.0386. Min Range: -3.0386

Max Act: 2.3178. Min Act: -0.0000

Data Index: 1604897 (Python Code)

Max Activating Token Index: 241

Text #18

Max Range: 3.0386. Min Range: -3.0386

Max Act: 2.0645. Min Act: -0.0000

Data Index: 1380899 (Python Code)

Max Activating Token Index: 403

Text #19

Max Range: 3.0386. Min Range: -3.0386

Max Act: 2.0530. Min Act: -0.0000

Data Index: 1630868 (Python Code)

Max Activating Token Index: 366