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

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

Neuron 5687 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.1036. Min Act: -0.0000

Data Index: 46018 (C4 (Web Text))

Max Activating Token Index: 895

Text #1

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.1053. Min Act: -0.0000

Data Index: 943176 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.1066. Min Act: -0.0000

Data Index: 207920 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0908. Min Act: -0.0000

Data Index: 599867 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0983. Min Act: -0.0000

Data Index: 711857 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0929. Min Act: -0.0000

Data Index: 1100432 (C4 (Web Text))

Max Activating Token Index: 415

Text #6

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0941. Min Act: -0.0000

Data Index: 51773 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0906. Min Act: -0.0000

Data Index: 813224 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0836. Min Act: -0.0000

Data Index: 321140 (C4 (Web Text))

Max Activating Token Index: 203

Text #9

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0936. Min Act: -0.0000

Data Index: 137598 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0879. Min Act: -0.0000

Data Index: 1225707 (C4 (Web Text))

Max Activating Token Index: 447

Text #11

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0793. Min Act: -0.0000

Data Index: 229759 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0777. Min Act: -0.0000

Data Index: 653624 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0750. Min Act: -0.0000

Data Index: 540594 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0826. Min Act: -0.0000

Data Index: 88176 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0795. Min Act: -0.0000

Data Index: 203689 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0767. Min Act: -0.0000

Data Index: 711599 (C4 (Web Text))

Max Activating Token Index: 561

Text #17

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0753. Min Act: -0.0000

Data Index: 1111887 (C4 (Web Text))

Max Activating Token Index: 153

Text #18

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0736. Min Act: -0.0000

Data Index: 621183 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0689. Min Act: -0.0000

Data Index: 1000784 (C4 (Web Text))

Max Activating Token Index: 553