Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2578 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0313. Min Act: -0.0003

Data Index: 1385888 (Python Code)

Max Activating Token Index: 40

Text #1

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0310. Min Act: -0.0003

Data Index: 1653519 (Python Code)

Max Activating Token Index: 45

Text #2

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0301. Min Act: -0.0003

Data Index: 1411333 (Python Code)

Max Activating Token Index: 118

Text #3

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0293. Min Act: -0.0003

Data Index: 1568529 (Python Code)

Max Activating Token Index: 292

Text #4

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0313. Min Act: -0.0003

Data Index: 1440237 (Python Code)

Max Activating Token Index: 5

Text #5

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0301. Min Act: -0.0003

Data Index: 1478088 (Python Code)

Max Activating Token Index: 44

Text #6

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0297. Min Act: -0.0003

Data Index: 1571424 (Python Code)

Max Activating Token Index: 905

Text #7

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0314. Min Act: -0.0003

Data Index: 1544727 (Python Code)

Max Activating Token Index: 706

Text #8

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0282. Min Act: -0.0003

Data Index: 1634790 (Python Code)

Max Activating Token Index: 747

Text #9

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0292. Min Act: -0.0003

Data Index: 1450446 (Python Code)

Max Activating Token Index: 21

Text #10

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0293. Min Act: -0.0003

Data Index: 1403578 (Python Code)

Max Activating Token Index: 1004

Text #11

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0292. Min Act: -0.0003

Data Index: 1361438 (Python Code)

Max Activating Token Index: 59

Text #12

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0294. Min Act: -0.0003

Data Index: 1466109 (Python Code)

Max Activating Token Index: 114

Text #13

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0288. Min Act: -0.0003

Data Index: 1448937 (Python Code)

Max Activating Token Index: 256

Text #14

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0284. Min Act: -0.0003

Data Index: 1437688 (Python Code)

Max Activating Token Index: 256

Text #15

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0288. Min Act: -0.0003

Data Index: 1392429 (Python Code)

Max Activating Token Index: 94

Text #16

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0288. Min Act: -0.0003

Data Index: 1410192 (Python Code)

Max Activating Token Index: 14

Text #17

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0286. Min Act: -0.0003

Data Index: 1645686 (Python Code)

Max Activating Token Index: 33

Text #18

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0275. Min Act: -0.0003

Data Index: 1366505 (Python Code)

Max Activating Token Index: 853

Text #19

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0276. Min Act: -0.0003

Data Index: 1590775 (Python Code)

Max Activating Token Index: 201