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

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

Neuron 3709 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: 2.3612. Min Range: -2.3612

Max Act: 2.3612. Min Act: -0.0000

Data Index: 1387162 (Python Code)

Max Activating Token Index: 936

Text #1

Max Range: 2.3612. Min Range: -2.3612

Max Act: 2.2360. Min Act: -0.0000

Data Index: 1514491 (Python Code)

Max Activating Token Index: 1012

Text #2

Max Range: 2.3612. Min Range: -2.3612

Max Act: 2.2008. Min Act: -0.0000

Data Index: 1579537 (Python Code)

Max Activating Token Index: 220

Text #3

Max Range: 2.3612. Min Range: -2.3612

Max Act: 2.1212. Min Act: -0.0000

Data Index: 1481533 (Python Code)

Max Activating Token Index: 392

Text #4

Max Range: 2.3612. Min Range: -2.3612

Max Act: 2.1541. Min Act: -0.0000

Data Index: 1551312 (Python Code)

Max Activating Token Index: 716

Text #5

Max Range: 2.3612. Min Range: -2.3612

Max Act: 1.9731. Min Act: -0.0000

Data Index: 1487519 (Python Code)

Max Activating Token Index: 98

Text #6

Max Range: 2.3612. Min Range: -2.3612

Max Act: 2.0125. Min Act: -0.0000

Data Index: 1380560 (Python Code)

Max Activating Token Index: 363

Text #7

Max Range: 2.3612. Min Range: -2.3612

Max Act: 1.9898. Min Act: -0.0000

Data Index: 991696 (C4 (Web Text))

Max Activating Token Index: 367

Text #8

Max Range: 2.3612. Min Range: -2.3612

Max Act: 1.8707. Min Act: -0.0000

Data Index: 1500470 (Python Code)

Max Activating Token Index: 162

Text #9

Max Range: 2.3612. Min Range: -2.3612

Max Act: 1.8383. Min Act: -0.0000

Data Index: 1479188 (Python Code)

Max Activating Token Index: 199

Text #10

Max Range: 2.3612. Min Range: -2.3612

Max Act: 1.9313. Min Act: -0.0000

Data Index: 1385475 (Python Code)

Max Activating Token Index: 987

Text #11

Max Range: 2.3612. Min Range: -2.3612

Max Act: 1.9280. Min Act: -0.0000

Data Index: 1438666 (Python Code)

Max Activating Token Index: 819

Text #12

Max Range: 2.3612. Min Range: -2.3612

Max Act: 2.0220. Min Act: -0.0000

Data Index: 1392586 (Python Code)

Max Activating Token Index: 196

Text #13

Max Range: 2.3612. Min Range: -2.3612

Max Act: 1.9016. Min Act: -0.0000

Data Index: 1402856 (Python Code)

Max Activating Token Index: 432

Text #14

Max Range: 2.3612. Min Range: -2.3612

Max Act: 1.8663. Min Act: -0.0000

Data Index: 1562931 (Python Code)

Max Activating Token Index: 452

Text #15

Max Range: 2.3612. Min Range: -2.3612

Max Act: 1.7496. Min Act: -0.0000

Data Index: 1607620 (Python Code)

Max Activating Token Index: 89

Text #16

Max Range: 2.3612. Min Range: -2.3612

Max Act: 1.8009. Min Act: -0.0000

Data Index: 1482218 (Python Code)

Max Activating Token Index: 561

Text #17

Max Range: 2.3612. Min Range: -2.3612

Max Act: 1.7554. Min Act: -0.0000

Data Index: 1368441 (Python Code)

Max Activating Token Index: 90

Text #18

Max Range: 2.3612. Min Range: -2.3612

Max Act: 1.7094. Min Act: -0.0000

Data Index: 1473178 (Python Code)

Max Activating Token Index: 998

Text #19

Max Range: 2.3612. Min Range: -2.3612

Max Act: 1.6003. Min Act: -0.0000

Data Index: 1498600 (Python Code)

Max Activating Token Index: 356