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

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

Neuron 5785 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: 2.0433. Min Range: -2.0433

Max Act: 2.0433. Min Act: -0.0000

Data Index: 1426242 (Python Code)

Max Activating Token Index: 79

Text #1

Max Range: 2.0433. Min Range: -2.0433

Max Act: 1.7090. Min Act: -0.0000

Data Index: 73004 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 2.0433. Min Range: -2.0433

Max Act: 1.3524. Min Act: -0.0000

Data Index: 1434370 (Python Code)

Max Activating Token Index: 968

Text #3

Max Range: 2.0433. Min Range: -2.0433

Max Act: 1.4634. Min Act: -0.0000

Data Index: 993728 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 2.0433. Min Range: -2.0433

Max Act: 1.2750. Min Act: -0.0000

Data Index: 1494365 (Python Code)

Max Activating Token Index: 992

Text #5

Max Range: 2.0433. Min Range: -2.0433

Max Act: 1.2099. Min Act: -0.0000

Data Index: 1563162 (Python Code)

Max Activating Token Index: 398

Text #6

Max Range: 2.0433. Min Range: -2.0433

Max Act: 1.1162. Min Act: -0.0000

Data Index: 1600850 (Python Code)

Max Activating Token Index: 599

Text #7

Max Range: 2.0433. Min Range: -2.0433

Max Act: 1.1617. Min Act: -0.0000

Data Index: 1389302 (Python Code)

Max Activating Token Index: 913

Text #8

Max Range: 2.0433. Min Range: -2.0433

Max Act: 1.1240. Min Act: -0.0000

Data Index: 1556057 (Python Code)

Max Activating Token Index: 1011

Text #9

Max Range: 2.0433. Min Range: -2.0433

Max Act: 1.1318. Min Act: -0.0000

Data Index: 1635867 (Python Code)

Max Activating Token Index: 781

Text #10

Max Range: 2.0433. Min Range: -2.0433

Max Act: 1.1166. Min Act: -0.0000

Data Index: 1516844 (Python Code)

Max Activating Token Index: 500

Text #11

Max Range: 2.0433. Min Range: -2.0433

Max Act: 1.1071. Min Act: -0.0000

Data Index: 1616715 (Python Code)

Max Activating Token Index: 394

Text #12

Max Range: 2.0433. Min Range: -2.0433

Max Act: 1.0633. Min Act: -0.0000

Data Index: 1523473 (Python Code)

Max Activating Token Index: 224

Text #13

Max Range: 2.0433. Min Range: -2.0433

Max Act: 1.1436. Min Act: -0.0000

Data Index: 1460723 (Python Code)

Max Activating Token Index: 860

Text #14

Max Range: 2.0433. Min Range: -2.0433

Max Act: 1.0369. Min Act: -0.0000

Data Index: 1545918 (Python Code)

Max Activating Token Index: 184

Text #15

Max Range: 2.0433. Min Range: -2.0433

Max Act: 1.0486. Min Act: -0.0000

Data Index: 1371371 (Python Code)

Max Activating Token Index: 984

Text #16

Max Range: 2.0433. Min Range: -2.0433

Max Act: 1.0004. Min Act: -0.0000

Data Index: 1398197 (Python Code)

Max Activating Token Index: 213

Text #17

Max Range: 2.0433. Min Range: -2.0433

Max Act: 1.0524. Min Act: -0.0000

Data Index: 1396454 (Python Code)

Max Activating Token Index: 41

Text #18

Max Range: 2.0433. Min Range: -2.0433

Max Act: 1.0145. Min Act: -0.0000

Data Index: 1586047 (Python Code)

Max Activating Token Index: 384

Text #19

Max Range: 2.0433. Min Range: -2.0433

Max Act: 1.0167. Min Act: -0.0000

Data Index: 1442932 (Python Code)

Max Activating Token Index: 13