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

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

Neuron 1813 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.6829. Min Act: -0.0000

Data Index: 1511397 (Python Code)

Max Activating Token Index: 890

Text #1

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.6277. Min Act: -0.0000

Data Index: 1548811 (Python Code)

Max Activating Token Index: 489

Text #2

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.6183. Min Act: -0.0000

Data Index: 1426360 (Python Code)

Max Activating Token Index: 205

Text #3

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.6049. Min Act: -0.0000

Data Index: 1651882 (Python Code)

Max Activating Token Index: 856

Text #4

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.5729. Min Act: -0.0000

Data Index: 1502136 (Python Code)

Max Activating Token Index: 509

Text #5

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.5113. Min Act: -0.0000

Data Index: 1398305 (Python Code)

Max Activating Token Index: 153

Text #6

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.4995. Min Act: -0.0000

Data Index: 1398793 (Python Code)

Max Activating Token Index: 140

Text #7

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.5530. Min Act: -0.0000

Data Index: 1482053 (Python Code)

Max Activating Token Index: 980

Text #8

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.5107. Min Act: -0.0000

Data Index: 1531062 (Python Code)

Max Activating Token Index: 752

Text #9

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.5016. Min Act: -0.0000

Data Index: 1613182 (Python Code)

Max Activating Token Index: 320

Text #10

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.5175. Min Act: -0.0000

Data Index: 1362106 (Python Code)

Max Activating Token Index: 842

Text #11

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.4985. Min Act: -0.0000

Data Index: 1539360 (Python Code)

Max Activating Token Index: 659

Text #12

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.4748. Min Act: -0.0000

Data Index: 1475963 (Python Code)

Max Activating Token Index: 800

Text #13

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.4686. Min Act: -0.0000

Data Index: 1635848 (Python Code)

Max Activating Token Index: 508

Text #14

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.4216. Min Act: -0.0000

Data Index: 1505688 (Python Code)

Max Activating Token Index: 298

Text #15

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.4808. Min Act: -0.0000

Data Index: 1465079 (Python Code)

Max Activating Token Index: 115

Text #16

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.4903. Min Act: -0.0000

Data Index: 1608569 (Python Code)

Max Activating Token Index: 851

Text #17

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.4911. Min Act: -0.0000

Data Index: 1381695 (Python Code)

Max Activating Token Index: 820

Text #18

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.4573. Min Act: -0.0000

Data Index: 1562837 (Python Code)

Max Activating Token Index: 284

Text #19

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.4531. Min Act: -0.0000

Data Index: 1616019 (Python Code)

Max Activating Token Index: 144