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

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

Neuron 4907 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: 2.8802. Min Range: -2.8802

Max Act: 2.8802. Min Act: 0.0000

Data Index: 1411520 (Python Code)

Max Activating Token Index: 617

Text #1

Max Range: 2.8802. Min Range: -2.8802

Max Act: 2.6828. Min Act: -0.0000

Data Index: 1493702 (Python Code)

Max Activating Token Index: 785

Text #2

Max Range: 2.8802. Min Range: -2.8802

Max Act: 2.4696. Min Act: -0.0000

Data Index: 1494032 (Python Code)

Max Activating Token Index: 733

Text #3

Max Range: 2.8802. Min Range: -2.8802

Max Act: 2.5465. Min Act: -0.0000

Data Index: 1540079 (Python Code)

Max Activating Token Index: 306

Text #4

Max Range: 2.8802. Min Range: -2.8802

Max Act: 2.6975. Min Act: -0.0000

Data Index: 1575141 (Python Code)

Max Activating Token Index: 633

Text #5

Max Range: 2.8802. Min Range: -2.8802

Max Act: 2.4533. Min Act: -0.0000

Data Index: 1644864 (Python Code)

Max Activating Token Index: 622

Text #6

Max Range: 2.8802. Min Range: -2.8802

Max Act: 2.2984. Min Act: 0.0000

Data Index: 1538026 (Python Code)

Max Activating Token Index: 756

Text #7

Max Range: 2.8802. Min Range: -2.8802

Max Act: 2.3852. Min Act: -0.0000

Data Index: 1522921 (Python Code)

Max Activating Token Index: 44

Text #8

Max Range: 2.8802. Min Range: -2.8802

Max Act: 2.3708. Min Act: -0.0000

Data Index: 1483362 (Python Code)

Max Activating Token Index: 864

Text #9

Max Range: 2.8802. Min Range: -2.8802

Max Act: 2.2490. Min Act: -0.0000

Data Index: 1373780 (Python Code)

Max Activating Token Index: 390

Text #10

Max Range: 2.8802. Min Range: -2.8802

Max Act: 2.3672. Min Act: -0.0000

Data Index: 1644028 (Python Code)

Max Activating Token Index: 170

Text #11

Max Range: 2.8802. Min Range: -2.8802

Max Act: 2.3171. Min Act: -0.0000

Data Index: 1504409 (Python Code)

Max Activating Token Index: 959

Text #12

Max Range: 2.8802. Min Range: -2.8802

Max Act: 2.2880. Min Act: -0.0000

Data Index: 1440976 (Python Code)

Max Activating Token Index: 451

Text #13

Max Range: 2.8802. Min Range: -2.8802

Max Act: 2.2705. Min Act: -0.0000

Data Index: 1577464 (Python Code)

Max Activating Token Index: 86

Text #14

Max Range: 2.8802. Min Range: -2.8802

Max Act: 2.0243. Min Act: -0.0000

Data Index: 1485653 (Python Code)

Max Activating Token Index: 822

Text #15

Max Range: 2.8802. Min Range: -2.8802

Max Act: 2.3545. Min Act: 0.0000

Data Index: 1580448 (Python Code)

Max Activating Token Index: 970

Text #16

Max Range: 2.8802. Min Range: -2.8802

Max Act: 2.1184. Min Act: 0.0000

Data Index: 1460682 (Python Code)

Max Activating Token Index: 178

Text #17

Max Range: 2.8802. Min Range: -2.8802

Max Act: 2.2285. Min Act: -0.0000

Data Index: 1376758 (Python Code)

Max Activating Token Index: 57

Text #18

Max Range: 2.8802. Min Range: -2.8802

Max Act: 2.1221. Min Act: -0.0000

Data Index: 1500475 (Python Code)

Max Activating Token Index: 773

Text #19

Max Range: 2.8802. Min Range: -2.8802

Max Act: 2.3418. Min Act: -0.0000

Data Index: 1630104 (Python Code)

Max Activating Token Index: 711