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

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

Neuron 2822 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3722. Min Range: -2.3722

Max Act: 2.3722. Min Act: -0.0000

Data Index: 1426101 (Python Code)

Max Activating Token Index: 229

Text #1

Max Range: 2.3722. Min Range: -2.3722

Max Act: 2.1976. Min Act: -0.0000

Data Index: 1655407 (Python Code)

Max Activating Token Index: 956

Text #2

Max Range: 2.3722. Min Range: -2.3722

Max Act: 2.1796. Min Act: -0.0000

Data Index: 1490476 (Python Code)

Max Activating Token Index: 132

Text #3

Max Range: 2.3722. Min Range: -2.3722

Max Act: 2.1470. Min Act: -0.0000

Data Index: 1389829 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 2.3722. Min Range: -2.3722

Max Act: 1.9546. Min Act: -0.0000

Data Index: 1486131 (Python Code)

Max Activating Token Index: 425

Text #5

Max Range: 2.3722. Min Range: -2.3722

Max Act: 1.9264. Min Act: -0.0000

Data Index: 1623436 (Python Code)

Max Activating Token Index: 922

Text #6

Max Range: 2.3722. Min Range: -2.3722

Max Act: 1.8985. Min Act: -0.0000

Data Index: 1648838 (Python Code)

Max Activating Token Index: 337

Text #7

Max Range: 2.3722. Min Range: -2.3722

Max Act: 1.9909. Min Act: -0.0000

Data Index: 1573050 (Python Code)

Max Activating Token Index: 1005

Text #8

Max Range: 2.3722. Min Range: -2.3722

Max Act: 1.9247. Min Act: -0.0000

Data Index: 1367379 (Python Code)

Max Activating Token Index: 142

Text #9

Max Range: 2.3722. Min Range: -2.3722

Max Act: 1.8187. Min Act: -0.0000

Data Index: 1531897 (Python Code)

Max Activating Token Index: 366

Text #10

Max Range: 2.3722. Min Range: -2.3722

Max Act: 1.6612. Min Act: -0.0000

Data Index: 1548284 (Python Code)

Max Activating Token Index: 771

Text #11

Max Range: 2.3722. Min Range: -2.3722

Max Act: 1.7008. Min Act: -0.0000

Data Index: 1623903 (Python Code)

Max Activating Token Index: 89

Text #12

Max Range: 2.3722. Min Range: -2.3722

Max Act: 1.7976. Min Act: -0.0000

Data Index: 1448147 (Python Code)

Max Activating Token Index: 917

Text #13

Max Range: 2.3722. Min Range: -2.3722

Max Act: 1.7232. Min Act: -0.0000

Data Index: 1438863 (Python Code)

Max Activating Token Index: 618

Text #14

Max Range: 2.3722. Min Range: -2.3722

Max Act: 1.5156. Min Act: -0.0000

Data Index: 1371196 (Python Code)

Max Activating Token Index: 358

Text #15

Max Range: 2.3722. Min Range: -2.3722

Max Act: 1.4327. Min Act: -0.0000

Data Index: 1518464 (Python Code)

Max Activating Token Index: 102

Text #16

Max Range: 2.3722. Min Range: -2.3722

Max Act: 1.6329. Min Act: -0.0000

Data Index: 1386266 (Python Code)

Max Activating Token Index: 720

Text #17

Max Range: 2.3722. Min Range: -2.3722

Max Act: 1.5736. Min Act: -0.0000

Data Index: 1540774 (Python Code)

Max Activating Token Index: 781

Text #18

Max Range: 2.3722. Min Range: -2.3722

Max Act: 1.5365. Min Act: -0.0000

Data Index: 1484971 (Python Code)

Max Activating Token Index: 669

Text #19

Max Range: 2.3722. Min Range: -2.3722

Max Act: 1.5220. Min Act: -0.0000

Data Index: 1446996 (Python Code)

Max Activating Token Index: 560