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

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

Neuron 5912 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: 1.2090. Min Range: -1.2090

Max Act: 1.2090. Min Act: -0.0000

Data Index: 1413359 (Python Code)

Max Activating Token Index: 114

Text #1

Max Range: 1.2090. Min Range: -1.2090

Max Act: 1.1739. Min Act: -0.0000

Data Index: 1499971 (Python Code)

Max Activating Token Index: 116

Text #2

Max Range: 1.2090. Min Range: -1.2090

Max Act: 1.1300. Min Act: -0.0000

Data Index: 1652005 (Python Code)

Max Activating Token Index: 111

Text #3

Max Range: 1.2090. Min Range: -1.2090

Max Act: 1.1650. Min Act: -0.0000

Data Index: 1569907 (Python Code)

Max Activating Token Index: 150

Text #4

Max Range: 1.2090. Min Range: -1.2090

Max Act: 1.1619. Min Act: -0.0000

Data Index: 1566272 (Python Code)

Max Activating Token Index: 128

Text #5

Max Range: 1.2090. Min Range: -1.2090

Max Act: 1.0277. Min Act: -0.0000

Data Index: 1372603 (Python Code)

Max Activating Token Index: 143

Text #6

Max Range: 1.2090. Min Range: -1.2090

Max Act: 1.0112. Min Act: -0.0000

Data Index: 123145 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 1.2090. Min Range: -1.2090

Max Act: 0.9998. Min Act: -0.0000

Data Index: 168082 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 1.2090. Min Range: -1.2090

Max Act: 0.9480. Min Act: -0.0000

Data Index: 1480181 (Python Code)

Max Activating Token Index: 469

Text #9

Max Range: 1.2090. Min Range: -1.2090

Max Act: 0.7723. Min Act: -0.0000

Data Index: 1088939 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 1.2090. Min Range: -1.2090

Max Act: 0.9132. Min Act: -0.0000

Data Index: 651686 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 1.2090. Min Range: -1.2090

Max Act: 0.7715. Min Act: -0.0000

Data Index: 982704 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 1.2090. Min Range: -1.2090

Max Act: 0.8644. Min Act: -0.0000

Data Index: 87311 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 1.2090. Min Range: -1.2090

Max Act: 0.7652. Min Act: -0.0000

Data Index: 218009 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 1.2090. Min Range: -1.2090

Max Act: 0.7786. Min Act: -0.0000

Data Index: 1255094 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 1.2090. Min Range: -1.2090

Max Act: 0.8500. Min Act: -0.0000

Data Index: 1276421 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 1.2090. Min Range: -1.2090

Max Act: 0.7959. Min Act: -0.0000

Data Index: 279738 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 1.2090. Min Range: -1.2090

Max Act: 0.7891. Min Act: -0.0000

Data Index: 898716 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 1.2090. Min Range: -1.2090

Max Act: 0.7646. Min Act: -0.0000

Data Index: 359375 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 1.2090. Min Range: -1.2090

Max Act: 0.7577. Min Act: -0.0000

Data Index: 764326 (C4 (Web Text))

Max Activating Token Index: 572