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

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

Neuron 5656 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7987. Min Range: -2.7987

Max Act: 2.7987. Min Act: -0.0000

Data Index: 1438630 (Python Code)

Max Activating Token Index: 525

Text #1

Max Range: 2.7987. Min Range: -2.7987

Max Act: 1.7076. Min Act: -0.0000

Data Index: 1430331 (Python Code)

Max Activating Token Index: 591

Text #2

Max Range: 2.7987. Min Range: -2.7987

Max Act: 1.4678. Min Act: -0.0000

Data Index: 1652758 (Python Code)

Max Activating Token Index: 733

Text #3

Max Range: 2.7987. Min Range: -2.7987

Max Act: 1.5386. Min Act: -0.0000

Data Index: 1559182 (Python Code)

Max Activating Token Index: 576

Text #4

Max Range: 2.7987. Min Range: -2.7987

Max Act: 1.3853. Min Act: -0.0000

Data Index: 1520900 (Python Code)

Max Activating Token Index: 972

Text #5

Max Range: 2.7987. Min Range: -2.7987

Max Act: 1.2608. Min Act: -0.0000

Data Index: 1596006 (Python Code)

Max Activating Token Index: 972

Text #6

Max Range: 2.7987. Min Range: -2.7987

Max Act: 1.2752. Min Act: -0.0000

Data Index: 1422418 (Python Code)

Max Activating Token Index: 377

Text #7

Max Range: 2.7987. Min Range: -2.7987

Max Act: 1.2695. Min Act: -0.0000

Data Index: 1571435 (Python Code)

Max Activating Token Index: 235

Text #8

Max Range: 2.7987. Min Range: -2.7987

Max Act: 1.3339. Min Act: -0.0000

Data Index: 1518465 (Python Code)

Max Activating Token Index: 396

Text #9

Max Range: 2.7987. Min Range: -2.7987

Max Act: 1.3106. Min Act: -0.0000

Data Index: 1538847 (Python Code)

Max Activating Token Index: 444

Text #10

Max Range: 2.7987. Min Range: -2.7987

Max Act: 1.2277. Min Act: -0.0000

Data Index: 1428456 (Python Code)

Max Activating Token Index: 433

Text #11

Max Range: 2.7987. Min Range: -2.7987

Max Act: 1.2202. Min Act: -0.0000

Data Index: 1449833 (Python Code)

Max Activating Token Index: 677

Text #12

Max Range: 2.7987. Min Range: -2.7987

Max Act: 1.2021. Min Act: -0.0000

Data Index: 1598411 (Python Code)

Max Activating Token Index: 497

Text #13

Max Range: 2.7987. Min Range: -2.7987

Max Act: 1.1587. Min Act: -0.0000

Data Index: 1652071 (Python Code)

Max Activating Token Index: 93

Text #14

Max Range: 2.7987. Min Range: -2.7987

Max Act: 1.2279. Min Act: -0.0000

Data Index: 1418688 (Python Code)

Max Activating Token Index: 872

Text #15

Max Range: 2.7987. Min Range: -2.7987

Max Act: 1.2124. Min Act: -0.0000

Data Index: 1492608 (Python Code)

Max Activating Token Index: 780

Text #16

Max Range: 2.7987. Min Range: -2.7987

Max Act: 1.1619. Min Act: -0.0000

Data Index: 1585463 (Python Code)

Max Activating Token Index: 408

Text #17

Max Range: 2.7987. Min Range: -2.7987

Max Act: 1.2040. Min Act: -0.0000

Data Index: 1421771 (Python Code)

Max Activating Token Index: 194

Text #18

Max Range: 2.7987. Min Range: -2.7987

Max Act: 1.1501. Min Act: -0.0000

Data Index: 1405785 (Python Code)

Max Activating Token Index: 596

Text #19

Max Range: 2.7987. Min Range: -2.7987

Max Act: 1.1110. Min Act: -0.0000

Data Index: 1574514 (Python Code)

Max Activating Token Index: 364