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

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

Neuron 2276 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0196. Min Range: -2.0196

Max Act: 2.0196. Min Act: -0.0000

Data Index: 1442129 (Python Code)

Max Activating Token Index: 931

Text #1

Max Range: 2.0196. Min Range: -2.0196

Max Act: 1.5985. Min Act: -0.0000

Data Index: 1417470 (Python Code)

Max Activating Token Index: 147

Text #2

Max Range: 2.0196. Min Range: -2.0196

Max Act: 1.3660. Min Act: -0.0000

Data Index: 1470474 (Python Code)

Max Activating Token Index: 571

Text #3

Max Range: 2.0196. Min Range: -2.0196

Max Act: 1.3752. Min Act: -0.0000

Data Index: 1398618 (Python Code)

Max Activating Token Index: 805

Text #4

Max Range: 2.0196. Min Range: -2.0196

Max Act: 1.3365. Min Act: -0.0000

Data Index: 1646920 (Python Code)

Max Activating Token Index: 742

Text #5

Max Range: 2.0196. Min Range: -2.0196

Max Act: 1.2986. Min Act: -0.0000

Data Index: 1592863 (Python Code)

Max Activating Token Index: 564

Text #6

Max Range: 2.0196. Min Range: -2.0196

Max Act: 1.3784. Min Act: -0.0000

Data Index: 1535230 (Python Code)

Max Activating Token Index: 155

Text #7

Max Range: 2.0196. Min Range: -2.0196

Max Act: 1.1880. Min Act: -0.0000

Data Index: 1377290 (Python Code)

Max Activating Token Index: 325

Text #8

Max Range: 2.0196. Min Range: -2.0196

Max Act: 1.3538. Min Act: -0.0000

Data Index: 1421915 (Python Code)

Max Activating Token Index: 869

Text #9

Max Range: 2.0196. Min Range: -2.0196

Max Act: 1.2321. Min Act: -0.0000

Data Index: 1597014 (Python Code)

Max Activating Token Index: 247

Text #10

Max Range: 2.0196. Min Range: -2.0196

Max Act: 1.2676. Min Act: -0.0000

Data Index: 1624696 (Python Code)

Max Activating Token Index: 413

Text #11

Max Range: 2.0196. Min Range: -2.0196

Max Act: 1.0951. Min Act: -0.0000

Data Index: 1635482 (Python Code)

Max Activating Token Index: 813

Text #12

Max Range: 2.0196. Min Range: -2.0196

Max Act: 1.0904. Min Act: -0.0000

Data Index: 1553094 (Python Code)

Max Activating Token Index: 29

Text #13

Max Range: 2.0196. Min Range: -2.0196

Max Act: 1.1105. Min Act: 0.0000

Data Index: 1371134 (Python Code)

Max Activating Token Index: 109

Text #14

Max Range: 2.0196. Min Range: -2.0196

Max Act: 1.0632. Min Act: -0.0000

Data Index: 1401294 (Python Code)

Max Activating Token Index: 240

Text #15

Max Range: 2.0196. Min Range: -2.0196

Max Act: 1.0956. Min Act: -0.0000

Data Index: 1504577 (Python Code)

Max Activating Token Index: 955

Text #16

Max Range: 2.0196. Min Range: -2.0196

Max Act: 1.0865. Min Act: -0.0000

Data Index: 1568433 (Python Code)

Max Activating Token Index: 488

Text #17

Max Range: 2.0196. Min Range: -2.0196

Max Act: 1.1717. Min Act: -0.0000

Data Index: 1452875 (Python Code)

Max Activating Token Index: 959

Text #18

Max Range: 2.0196. Min Range: -2.0196

Max Act: 1.0501. Min Act: -0.0000

Data Index: 1540869 (Python Code)

Max Activating Token Index: 570

Text #19

Max Range: 2.0196. Min Range: -2.0196

Max Act: 1.0058. Min Act: -0.0000

Data Index: 1440047 (Python Code)

Max Activating Token Index: 100