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

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

Neuron 4480 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: 0.7688. Min Range: -0.7688

Max Act: 0.7688. Min Act: -0.0000

Data Index: 1481358 (Python Code)

Max Activating Token Index: 992

Text #1

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.7522. Min Act: -0.0000

Data Index: 1619704 (Python Code)

Max Activating Token Index: 896

Text #2

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.7271. Min Act: -0.0000

Data Index: 1619958 (Python Code)

Max Activating Token Index: 346

Text #3

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.7565. Min Act: -0.0000

Data Index: 1406477 (Python Code)

Max Activating Token Index: 268

Text #4

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.7656. Min Act: -0.0000

Data Index: 1484729 (Python Code)

Max Activating Token Index: 406

Text #5

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.7131. Min Act: -0.0000

Data Index: 1578386 (Python Code)

Max Activating Token Index: 822

Text #6

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.7330. Min Act: -0.0000

Data Index: 1509845 (Python Code)

Max Activating Token Index: 94

Text #7

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.7387. Min Act: -0.0000

Data Index: 1403674 (Python Code)

Max Activating Token Index: 73

Text #8

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.7047. Min Act: -0.0000

Data Index: 1408580 (Python Code)

Max Activating Token Index: 510

Text #9

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6766. Min Act: -0.0000

Data Index: 1430886 (Python Code)

Max Activating Token Index: 270

Text #10

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6968. Min Act: -0.0000

Data Index: 1533751 (Python Code)

Max Activating Token Index: 552

Text #11

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.7134. Min Act: -0.0000

Data Index: 1559064 (Python Code)

Max Activating Token Index: 258

Text #12

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.7068. Min Act: -0.0000

Data Index: 1606819 (Python Code)

Max Activating Token Index: 869

Text #13

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.7321. Min Act: -0.0000

Data Index: 1576646 (Python Code)

Max Activating Token Index: 724

Text #14

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6830. Min Act: -0.0000

Data Index: 1469713 (Python Code)

Max Activating Token Index: 345

Text #15

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6588. Min Act: -0.0000

Data Index: 1647649 (Python Code)

Max Activating Token Index: 875

Text #16

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6143. Min Act: -0.0000

Data Index: 1415999 (Python Code)

Max Activating Token Index: 924

Text #17

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6571. Min Act: -0.0000

Data Index: 1535890 (Python Code)

Max Activating Token Index: 343

Text #18

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6288. Min Act: -0.0000

Data Index: 1459793 (Python Code)

Max Activating Token Index: 185

Text #19

Max Range: 0.7688. Min Range: -0.7688

Max Act: 0.6714. Min Act: -0.0000

Data Index: 1516144 (Python Code)

Max Activating Token Index: 437