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

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

Neuron 837 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2094. Min Range: -2.2094

Max Act: 2.2094. Min Act: -0.0000

Data Index: 1504398 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 2.2094. Min Range: -2.2094

Max Act: 1.9996. Min Act: -0.0000

Data Index: 1543141 (Python Code)

Max Activating Token Index: 139

Text #2

Max Range: 2.2094. Min Range: -2.2094

Max Act: 2.1017. Min Act: -0.0000

Data Index: 1556431 (Python Code)

Max Activating Token Index: 429

Text #3

Max Range: 2.2094. Min Range: -2.2094

Max Act: 1.9252. Min Act: -0.0000

Data Index: 1402047 (Python Code)

Max Activating Token Index: 733

Text #4

Max Range: 2.2094. Min Range: -2.2094

Max Act: 1.8984. Min Act: -0.0000

Data Index: 1422510 (Python Code)

Max Activating Token Index: 512

Text #5

Max Range: 2.2094. Min Range: -2.2094

Max Act: 1.8449. Min Act: -0.0000

Data Index: 1501474 (Python Code)

Max Activating Token Index: 578

Text #6

Max Range: 2.2094. Min Range: -2.2094

Max Act: 1.9362. Min Act: -0.0000

Data Index: 1422562 (Python Code)

Max Activating Token Index: 618

Text #7

Max Range: 2.2094. Min Range: -2.2094

Max Act: 1.8176. Min Act: -0.0000

Data Index: 1601939 (Python Code)

Max Activating Token Index: 379

Text #8

Max Range: 2.2094. Min Range: -2.2094

Max Act: 1.8170. Min Act: -0.0000

Data Index: 1569772 (Python Code)

Max Activating Token Index: 628

Text #9

Max Range: 2.2094. Min Range: -2.2094

Max Act: 1.8116. Min Act: -0.0000

Data Index: 1460584 (Python Code)

Max Activating Token Index: 210

Text #10

Max Range: 2.2094. Min Range: -2.2094

Max Act: 1.7968. Min Act: -0.0000

Data Index: 1401224 (Python Code)

Max Activating Token Index: 989

Text #11

Max Range: 2.2094. Min Range: -2.2094

Max Act: 1.9024. Min Act: -0.0000

Data Index: 1445282 (Python Code)

Max Activating Token Index: 992

Text #12

Max Range: 2.2094. Min Range: -2.2094

Max Act: 1.7001. Min Act: -0.0000

Data Index: 1460723 (Python Code)

Max Activating Token Index: 538

Text #13

Max Range: 2.2094. Min Range: -2.2094

Max Act: 1.7847. Min Act: -0.0000

Data Index: 1475574 (Python Code)

Max Activating Token Index: 792

Text #14

Max Range: 2.2094. Min Range: -2.2094

Max Act: 1.7669. Min Act: -0.0000

Data Index: 1603646 (Python Code)

Max Activating Token Index: 713

Text #15

Max Range: 2.2094. Min Range: -2.2094

Max Act: 1.7594. Min Act: -0.0000

Data Index: 1613346 (Python Code)

Max Activating Token Index: 262

Text #16

Max Range: 2.2094. Min Range: -2.2094

Max Act: 1.7570. Min Act: -0.0000

Data Index: 1396927 (Python Code)

Max Activating Token Index: 900

Text #17

Max Range: 2.2094. Min Range: -2.2094

Max Act: 1.7613. Min Act: -0.0000

Data Index: 1632933 (Python Code)

Max Activating Token Index: 149

Text #18

Max Range: 2.2094. Min Range: -2.2094

Max Act: 1.7639. Min Act: 0.0000

Data Index: 1492693 (Python Code)

Max Activating Token Index: 689

Text #19

Max Range: 2.2094. Min Range: -2.2094

Max Act: 1.7548. Min Act: -0.0000

Data Index: 1447597 (Python Code)

Max Activating Token Index: 801