Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1867 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.8708. Min Range: -4.8708

Max Act: 4.2228. Min Act: -0.0000

Data Index: 1362545 (Python Code)

Max Activating Token Index: 789

Text #1

Max Range: 4.8708. Min Range: -4.8708

Max Act: 4.5649. Min Act: -0.0000

Data Index: 1432800 (Python Code)

Max Activating Token Index: 522

Text #2

Max Range: 4.8708. Min Range: -4.8708

Max Act: 4.3787. Min Act: -0.0000

Data Index: 1484427 (Python Code)

Max Activating Token Index: 919

Text #3

Max Range: 4.8708. Min Range: -4.8708

Max Act: 4.8708. Min Act: 0.0000

Data Index: 1610649 (Python Code)

Max Activating Token Index: 823

Text #4

Max Range: 4.8708. Min Range: -4.8708

Max Act: 3.9072. Min Act: -0.0000

Data Index: 1579170 (Python Code)

Max Activating Token Index: 821

Text #5

Max Range: 4.8708. Min Range: -4.8708

Max Act: 3.8595. Min Act: -0.0000

Data Index: 1368066 (Python Code)

Max Activating Token Index: 583

Text #6

Max Range: 4.8708. Min Range: -4.8708

Max Act: 3.7930. Min Act: -0.0000

Data Index: 1486664 (Python Code)

Max Activating Token Index: 663

Text #7

Max Range: 4.8708. Min Range: -4.8708

Max Act: 3.4482. Min Act: -0.0000

Data Index: 1368894 (Python Code)

Max Activating Token Index: 346

Text #8

Max Range: 4.8708. Min Range: -4.8708

Max Act: 3.7250. Min Act: 0.0000

Data Index: 1474306 (Python Code)

Max Activating Token Index: 461

Text #9

Max Range: 4.8708. Min Range: -4.8708

Max Act: 3.7178. Min Act: 0.0000

Data Index: 1420694 (Python Code)

Max Activating Token Index: 687

Text #10

Max Range: 4.8708. Min Range: -4.8708

Max Act: 3.5371. Min Act: -0.0000

Data Index: 1458773 (Python Code)

Max Activating Token Index: 236

Text #11

Max Range: 4.8708. Min Range: -4.8708

Max Act: 3.8340. Min Act: -0.0000

Data Index: 1405271 (Python Code)

Max Activating Token Index: 536

Text #12

Max Range: 4.8708. Min Range: -4.8708

Max Act: 3.5475. Min Act: -0.0000

Data Index: 1415919 (Python Code)

Max Activating Token Index: 148

Text #13

Max Range: 4.8708. Min Range: -4.8708

Max Act: 3.3980. Min Act: -0.0000

Data Index: 1636765 (Python Code)

Max Activating Token Index: 972

Text #14

Max Range: 4.8708. Min Range: -4.8708

Max Act: 3.4941. Min Act: 0.0000

Data Index: 1634505 (Python Code)

Max Activating Token Index: 342

Text #15

Max Range: 4.8708. Min Range: -4.8708

Max Act: 3.4983. Min Act: -0.0000

Data Index: 1621403 (Python Code)

Max Activating Token Index: 134

Text #16

Max Range: 4.8708. Min Range: -4.8708

Max Act: 3.3391. Min Act: -0.0000

Data Index: 1570125 (Python Code)

Max Activating Token Index: 1011

Text #17

Max Range: 4.8708. Min Range: -4.8708

Max Act: 3.4052. Min Act: 0.0000

Data Index: 1380827 (Python Code)

Max Activating Token Index: 485

Text #18

Max Range: 4.8708. Min Range: -4.8708

Max Act: 3.3487. Min Act: -0.0000

Data Index: 1577012 (Python Code)

Max Activating Token Index: 205

Text #19

Max Range: 4.8708. Min Range: -4.8708

Max Act: 3.2885. Min Act: -0.0000

Data Index: 1374795 (Python Code)

Max Activating Token Index: 487