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

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

Neuron 3939 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: 0.9289. Min Range: -0.9289

Max Act: 0.9289. Min Act: -0.0000

Data Index: 1517200 (Python Code)

Max Activating Token Index: 581

Text #1

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.9227. Min Act: -0.0000

Data Index: 1532034 (Python Code)

Max Activating Token Index: 994

Text #2

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.9059. Min Act: -0.0000

Data Index: 1426249 (Python Code)

Max Activating Token Index: 265

Text #3

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.7747. Min Act: -0.0000

Data Index: 1399060 (Python Code)

Max Activating Token Index: 602

Text #4

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.8156. Min Act: -0.0000

Data Index: 1607567 (Python Code)

Max Activating Token Index: 826

Text #5

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.7695. Min Act: -0.0000

Data Index: 1512467 (Python Code)

Max Activating Token Index: 1001

Text #6

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.7392. Min Act: -0.0000

Data Index: 1516622 (Python Code)

Max Activating Token Index: 751

Text #7

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.7268. Min Act: -0.0000

Data Index: 1375686 (Python Code)

Max Activating Token Index: 421

Text #8

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6665. Min Act: -0.0000

Data Index: 1551457 (Python Code)

Max Activating Token Index: 48

Text #9

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.7092. Min Act: -0.0000

Data Index: 1513946 (Python Code)

Max Activating Token Index: 264

Text #10

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.7169. Min Act: -0.0000

Data Index: 1576840 (Python Code)

Max Activating Token Index: 79

Text #11

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6914. Min Act: -0.0000

Data Index: 1621607 (Python Code)

Max Activating Token Index: 186

Text #12

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.7684. Min Act: -0.0000

Data Index: 1497272 (Python Code)

Max Activating Token Index: 773

Text #13

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6836. Min Act: -0.0000

Data Index: 1647641 (Python Code)

Max Activating Token Index: 427

Text #14

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.7002. Min Act: -0.0000

Data Index: 1361782 (Python Code)

Max Activating Token Index: 71

Text #15

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6679. Min Act: -0.0000

Data Index: 1626362 (Python Code)

Max Activating Token Index: 245

Text #16

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6528. Min Act: -0.0000

Data Index: 1639715 (Python Code)

Max Activating Token Index: 84

Text #17

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6360. Min Act: -0.0000

Data Index: 1169251 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6317. Min Act: -0.0000

Data Index: 1542026 (Python Code)

Max Activating Token Index: 260

Text #19

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6250. Min Act: -0.0000

Data Index: 1446670 (Python Code)

Max Activating Token Index: 416