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

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

Neuron 4159 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: 1.4800. Min Range: -1.4800

Max Act: 1.4398. Min Act: -0.0000

Data Index: 1569224 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 1.4800. Min Range: -1.4800

Max Act: 1.4405. Min Act: -0.0000

Data Index: 1406063 (Python Code)

Max Activating Token Index: 200

Text #2

Max Range: 1.4800. Min Range: -1.4800

Max Act: 1.4800. Min Act: -0.0000

Data Index: 1403722 (Python Code)

Max Activating Token Index: 591

Text #3

Max Range: 1.4800. Min Range: -1.4800

Max Act: 1.4268. Min Act: -0.0000

Data Index: 1438701 (Python Code)

Max Activating Token Index: 860

Text #4

Max Range: 1.4800. Min Range: -1.4800

Max Act: 1.4095. Min Act: -0.0000

Data Index: 1468661 (Python Code)

Max Activating Token Index: 117

Text #5

Max Range: 1.4800. Min Range: -1.4800

Max Act: 1.3035. Min Act: -0.0000

Data Index: 1566360 (Python Code)

Max Activating Token Index: 730

Text #6

Max Range: 1.4800. Min Range: -1.4800

Max Act: 1.2836. Min Act: -0.0000

Data Index: 1473796 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 1.4800. Min Range: -1.4800

Max Act: 1.2762. Min Act: -0.0000

Data Index: 1446543 (Python Code)

Max Activating Token Index: 131

Text #8

Max Range: 1.4800. Min Range: -1.4800

Max Act: 1.2925. Min Act: -0.0000

Data Index: 1619287 (Python Code)

Max Activating Token Index: 137

Text #9

Max Range: 1.4800. Min Range: -1.4800

Max Act: 1.1982. Min Act: -0.0000

Data Index: 1484025 (Python Code)

Max Activating Token Index: 570

Text #10

Max Range: 1.4800. Min Range: -1.4800

Max Act: 1.1950. Min Act: -0.0000

Data Index: 1634667 (Python Code)

Max Activating Token Index: 374

Text #11

Max Range: 1.4800. Min Range: -1.4800

Max Act: 1.2009. Min Act: -0.0000

Data Index: 1531109 (Python Code)

Max Activating Token Index: 901

Text #12

Max Range: 1.4800. Min Range: -1.4800

Max Act: 1.2026. Min Act: -0.0000

Data Index: 1577644 (Python Code)

Max Activating Token Index: 510

Text #13

Max Range: 1.4800. Min Range: -1.4800

Max Act: 1.2357. Min Act: -0.0000

Data Index: 1470756 (Python Code)

Max Activating Token Index: 1019

Text #14

Max Range: 1.4800. Min Range: -1.4800

Max Act: 1.1606. Min Act: -0.0000

Data Index: 1632308 (Python Code)

Max Activating Token Index: 375

Text #15

Max Range: 1.4800. Min Range: -1.4800

Max Act: 1.1918. Min Act: -0.0000

Data Index: 1422167 (Python Code)

Max Activating Token Index: 844

Text #16

Max Range: 1.4800. Min Range: -1.4800

Max Act: 1.1530. Min Act: -0.0000

Data Index: 1561755 (Python Code)

Max Activating Token Index: 472

Text #17

Max Range: 1.4800. Min Range: -1.4800

Max Act: 1.1854. Min Act: -0.0000

Data Index: 1503428 (Python Code)

Max Activating Token Index: 338

Text #18

Max Range: 1.4800. Min Range: -1.4800

Max Act: 1.1512. Min Act: -0.0000

Data Index: 1522243 (Python Code)

Max Activating Token Index: 437

Text #19

Max Range: 1.4800. Min Range: -1.4800

Max Act: 1.2102. Min Act: -0.0000

Data Index: 1444997 (Python Code)

Max Activating Token Index: 423