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

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

Neuron 3842 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: 0.2933. Min Range: -0.2933

Max Act: 0.2933. Min Act: -0.0000

Data Index: 1423224 (Python Code)

Max Activating Token Index: 629

Text #1

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2733. Min Act: -0.0000

Data Index: 1481084 (Python Code)

Max Activating Token Index: 869

Text #2

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2772. Min Act: -0.0000

Data Index: 1508865 (Python Code)

Max Activating Token Index: 218

Text #3

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2739. Min Act: -0.0000

Data Index: 1565167 (Python Code)

Max Activating Token Index: 731

Text #4

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2431. Min Act: -0.0000

Data Index: 1591299 (Python Code)

Max Activating Token Index: 243

Text #5

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2316. Min Act: -0.0000

Data Index: 1598627 (Python Code)

Max Activating Token Index: 818

Text #6

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2068. Min Act: -0.0000

Data Index: 1361242 (Python Code)

Max Activating Token Index: 626

Text #7

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2290. Min Act: -0.0000

Data Index: 1532768 (Python Code)

Max Activating Token Index: 917

Text #8

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2152. Min Act: -0.0000

Data Index: 1370207 (Python Code)

Max Activating Token Index: 408

Text #9

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2264. Min Act: -0.0000

Data Index: 1438157 (Python Code)

Max Activating Token Index: 696

Text #10

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2149. Min Act: -0.0000

Data Index: 1588440 (Python Code)

Max Activating Token Index: 644

Text #11

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.1720. Min Act: -0.0000

Data Index: 1526216 (Python Code)

Max Activating Token Index: 320

Text #12

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2044. Min Act: -0.0000

Data Index: 1363612 (Python Code)

Max Activating Token Index: 556

Text #13

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.1942. Min Act: -0.0000

Data Index: 1438976 (Python Code)

Max Activating Token Index: 967

Text #14

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.1894. Min Act: -0.0000

Data Index: 1648580 (Python Code)

Max Activating Token Index: 675

Text #15

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2294. Min Act: -0.0000

Data Index: 1517951 (Python Code)

Max Activating Token Index: 887

Text #16

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.1902. Min Act: -0.0000

Data Index: 1524414 (Python Code)

Max Activating Token Index: 869

Text #17

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.1972. Min Act: -0.0000

Data Index: 1368121 (Python Code)

Max Activating Token Index: 467

Text #18

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.1850. Min Act: -0.0000

Data Index: 1522098 (Python Code)

Max Activating Token Index: 116

Text #19

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.1826. Min Act: -0.0000

Data Index: 1381811 (Python Code)

Max Activating Token Index: 318