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

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

Neuron 3581 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: 2.3377. Min Range: -2.3377

Max Act: 2.3377. Min Act: -0.0000

Data Index: 1553298 (Python Code)

Max Activating Token Index: 882

Text #1

Max Range: 2.3377. Min Range: -2.3377

Max Act: 2.3304. Min Act: -0.0000

Data Index: 1624295 (Python Code)

Max Activating Token Index: 537

Text #2

Max Range: 2.3377. Min Range: -2.3377

Max Act: 2.0377. Min Act: -0.0000

Data Index: 1578888 (Python Code)

Max Activating Token Index: 954

Text #3

Max Range: 2.3377. Min Range: -2.3377

Max Act: 2.0027. Min Act: -0.0000

Data Index: 1581620 (Python Code)

Max Activating Token Index: 258

Text #4

Max Range: 2.3377. Min Range: -2.3377

Max Act: 2.0608. Min Act: -0.0000

Data Index: 1464912 (Python Code)

Max Activating Token Index: 164

Text #5

Max Range: 2.3377. Min Range: -2.3377

Max Act: 2.0994. Min Act: -0.0000

Data Index: 1550412 (Python Code)

Max Activating Token Index: 827

Text #6

Max Range: 2.3377. Min Range: -2.3377

Max Act: 2.2746. Min Act: -0.0000

Data Index: 1450653 (Python Code)

Max Activating Token Index: 125

Text #7

Max Range: 2.3377. Min Range: -2.3377

Max Act: 1.9282. Min Act: -0.0000

Data Index: 1599918 (Python Code)

Max Activating Token Index: 565

Text #8

Max Range: 2.3377. Min Range: -2.3377

Max Act: 2.0091. Min Act: -0.0000

Data Index: 1388331 (Python Code)

Max Activating Token Index: 704

Text #9

Max Range: 2.3377. Min Range: -2.3377

Max Act: 2.0020. Min Act: -0.0000

Data Index: 1490332 (Python Code)

Max Activating Token Index: 858

Text #10

Max Range: 2.3377. Min Range: -2.3377

Max Act: 1.9577. Min Act: -0.0000

Data Index: 1629399 (Python Code)

Max Activating Token Index: 456

Text #11

Max Range: 2.3377. Min Range: -2.3377

Max Act: 1.9677. Min Act: -0.0000

Data Index: 1497876 (Python Code)

Max Activating Token Index: 551

Text #12

Max Range: 2.3377. Min Range: -2.3377

Max Act: 2.1730. Min Act: -0.0000

Data Index: 1554772 (Python Code)

Max Activating Token Index: 766

Text #13

Max Range: 2.3377. Min Range: -2.3377

Max Act: 1.9579. Min Act: -0.0000

Data Index: 1533331 (Python Code)

Max Activating Token Index: 70

Text #14

Max Range: 2.3377. Min Range: -2.3377

Max Act: 1.8108. Min Act: -0.0000

Data Index: 1643818 (Python Code)

Max Activating Token Index: 680

Text #15

Max Range: 2.3377. Min Range: -2.3377

Max Act: 1.9029. Min Act: -0.0000

Data Index: 1527493 (Python Code)

Max Activating Token Index: 144

Text #16

Max Range: 2.3377. Min Range: -2.3377

Max Act: 1.7889. Min Act: -0.0000

Data Index: 1498954 (Python Code)

Max Activating Token Index: 574

Text #17

Max Range: 2.3377. Min Range: -2.3377

Max Act: 1.8685. Min Act: -0.0000

Data Index: 1497941 (Python Code)

Max Activating Token Index: 688

Text #18

Max Range: 2.3377. Min Range: -2.3377

Max Act: 1.8490. Min Act: -0.0000

Data Index: 1372403 (Python Code)

Max Activating Token Index: 189

Text #19

Max Range: 2.3377. Min Range: -2.3377

Max Act: 1.8379. Min Act: -0.0000

Data Index: 1565267 (Python Code)

Max Activating Token Index: 919