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

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

Neuron 5502 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5893. Min Range: -2.5893

Max Act: 2.3862. Min Act: -0.0000

Data Index: 1425045 (Python Code)

Max Activating Token Index: 476

Text #1

Max Range: 2.5893. Min Range: -2.5893

Max Act: 2.5893. Min Act: -0.0000

Data Index: 1510891 (Python Code)

Max Activating Token Index: 743

Text #2

Max Range: 2.5893. Min Range: -2.5893

Max Act: 2.2490. Min Act: -0.0000

Data Index: 1601181 (Python Code)

Max Activating Token Index: 796

Text #3

Max Range: 2.5893. Min Range: -2.5893

Max Act: 2.2361. Min Act: -0.0000

Data Index: 1420166 (Python Code)

Max Activating Token Index: 926

Text #4

Max Range: 2.5893. Min Range: -2.5893

Max Act: 2.0915. Min Act: -0.0000

Data Index: 1399493 (Python Code)

Max Activating Token Index: 153

Text #5

Max Range: 2.5893. Min Range: -2.5893

Max Act: 2.0695. Min Act: -0.0000

Data Index: 1448059 (Python Code)

Max Activating Token Index: 838

Text #6

Max Range: 2.5893. Min Range: -2.5893

Max Act: 1.9377. Min Act: 0.0000

Data Index: 1613609 (Python Code)

Max Activating Token Index: 104

Text #7

Max Range: 2.5893. Min Range: -2.5893

Max Act: 1.8623. Min Act: 0.0000

Data Index: 1557772 (Python Code)

Max Activating Token Index: 286

Text #8

Max Range: 2.5893. Min Range: -2.5893

Max Act: 1.9252. Min Act: -0.0000

Data Index: 1509118 (Python Code)

Max Activating Token Index: 112

Text #9

Max Range: 2.5893. Min Range: -2.5893

Max Act: 1.7953. Min Act: -0.0000

Data Index: 1468780 (Python Code)

Max Activating Token Index: 133

Text #10

Max Range: 2.5893. Min Range: -2.5893

Max Act: 1.9339. Min Act: -0.0000

Data Index: 1570216 (Python Code)

Max Activating Token Index: 845

Text #11

Max Range: 2.5893. Min Range: -2.5893

Max Act: 1.8942. Min Act: -0.0000

Data Index: 1551977 (Python Code)

Max Activating Token Index: 904

Text #12

Max Range: 2.5893. Min Range: -2.5893

Max Act: 1.7179. Min Act: -0.0000

Data Index: 1595214 (Python Code)

Max Activating Token Index: 818

Text #13

Max Range: 2.5893. Min Range: -2.5893

Max Act: 1.7999. Min Act: -0.0000

Data Index: 1628228 (Python Code)

Max Activating Token Index: 130

Text #14

Max Range: 2.5893. Min Range: -2.5893

Max Act: 1.7753. Min Act: -0.0000

Data Index: 1630171 (Python Code)

Max Activating Token Index: 934

Text #15

Max Range: 2.5893. Min Range: -2.5893

Max Act: 1.8553. Min Act: -0.0000

Data Index: 1396893 (Python Code)

Max Activating Token Index: 274

Text #16

Max Range: 2.5893. Min Range: -2.5893

Max Act: 1.7417. Min Act: -0.0000

Data Index: 1647594 (Python Code)

Max Activating Token Index: 420

Text #17

Max Range: 2.5893. Min Range: -2.5893

Max Act: 1.8273. Min Act: -0.0000

Data Index: 1565613 (Python Code)

Max Activating Token Index: 322

Text #18

Max Range: 2.5893. Min Range: -2.5893

Max Act: 1.7994. Min Act: -0.0000

Data Index: 1545132 (Python Code)

Max Activating Token Index: 549

Text #19

Max Range: 2.5893. Min Range: -2.5893

Max Act: 1.6931. Min Act: -0.0000

Data Index: 1600228 (Python Code)

Max Activating Token Index: 44