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

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

Neuron 2477 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4048. Min Range: -1.4048

Max Act: 1.4048. Min Act: -0.0000

Data Index: 735778 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 1.4048. Min Range: -1.4048

Max Act: 1.2029. Min Act: -0.0000

Data Index: 1159989 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 1.4048. Min Range: -1.4048

Max Act: 1.0338. Min Act: -0.0000

Data Index: 535826 (C4 (Web Text))

Max Activating Token Index: 523

Text #3

Max Range: 1.4048. Min Range: -1.4048

Max Act: 1.0226. Min Act: -0.0000

Data Index: 58938 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 1.4048. Min Range: -1.4048

Max Act: 0.9713. Min Act: -0.0000

Data Index: 627083 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 1.4048. Min Range: -1.4048

Max Act: 0.9643. Min Act: -0.0000

Data Index: 917314 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 1.4048. Min Range: -1.4048

Max Act: 0.8919. Min Act: -0.0000

Data Index: 1068552 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 1.4048. Min Range: -1.4048

Max Act: 0.8807. Min Act: -0.0000

Data Index: 316312 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 1.4048. Min Range: -1.4048

Max Act: 0.9838. Min Act: -0.0000

Data Index: 1160132 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 1.4048. Min Range: -1.4048

Max Act: 0.8533. Min Act: -0.0000

Data Index: 1115232 (C4 (Web Text))

Max Activating Token Index: 811

Text #10

Max Range: 1.4048. Min Range: -1.4048

Max Act: 0.7991. Min Act: -0.0000

Data Index: 775664 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 1.4048. Min Range: -1.4048

Max Act: 0.8919. Min Act: -0.0000

Data Index: 371084 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 1.4048. Min Range: -1.4048

Max Act: 0.9110. Min Act: -0.0000

Data Index: 649557 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 1.4048. Min Range: -1.4048

Max Act: 0.8619. Min Act: -0.0000

Data Index: 1410683 (Python Code)

Max Activating Token Index: 259

Text #14

Max Range: 1.4048. Min Range: -1.4048

Max Act: 0.8998. Min Act: -0.0000

Data Index: 839252 (C4 (Web Text))

Max Activating Token Index: 732

Text #15

Max Range: 1.4048. Min Range: -1.4048

Max Act: 0.8403. Min Act: -0.0000

Data Index: 573476 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 1.4048. Min Range: -1.4048

Max Act: 0.8446. Min Act: -0.0000

Data Index: 778667 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 1.4048. Min Range: -1.4048

Max Act: 0.8108. Min Act: -0.0000

Data Index: 678084 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 1.4048. Min Range: -1.4048

Max Act: 0.8003. Min Act: -0.0000

Data Index: 1258775 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 1.4048. Min Range: -1.4048

Max Act: 0.7432. Min Act: -0.0000

Data Index: 661131 (C4 (Web Text))

Max Activating Token Index: 700