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

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

Neuron 135 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: 2.8780. Min Range: -2.8780

Max Act: 2.8780. Min Act: -0.0000

Data Index: 1640870 (Python Code)

Max Activating Token Index: 735

Text #1

Max Range: 2.8780. Min Range: -2.8780

Max Act: 2.8382. Min Act: -0.0000

Data Index: 1570508 (Python Code)

Max Activating Token Index: 571

Text #2

Max Range: 2.8780. Min Range: -2.8780

Max Act: 2.3263. Min Act: -0.0000

Data Index: 1464299 (Python Code)

Max Activating Token Index: 827

Text #3

Max Range: 2.8780. Min Range: -2.8780

Max Act: 2.2871. Min Act: -0.0000

Data Index: 1495233 (Python Code)

Max Activating Token Index: 563

Text #4

Max Range: 2.8780. Min Range: -2.8780

Max Act: 2.1537. Min Act: -0.0000

Data Index: 1411937 (Python Code)

Max Activating Token Index: 955

Text #5

Max Range: 2.8780. Min Range: -2.8780

Max Act: 2.2224. Min Act: -0.0000

Data Index: 1633001 (Python Code)

Max Activating Token Index: 642

Text #6

Max Range: 2.8780. Min Range: -2.8780

Max Act: 1.9006. Min Act: -0.0000

Data Index: 1591796 (Python Code)

Max Activating Token Index: 706

Text #7

Max Range: 2.8780. Min Range: -2.8780

Max Act: 2.1000. Min Act: -0.0000

Data Index: 1377944 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 2.8780. Min Range: -2.8780

Max Act: 2.0899. Min Act: -0.0000

Data Index: 1646012 (Python Code)

Max Activating Token Index: 915

Text #9

Max Range: 2.8780. Min Range: -2.8780

Max Act: 2.0593. Min Act: -0.0000

Data Index: 1505093 (Python Code)

Max Activating Token Index: 756

Text #10

Max Range: 2.8780. Min Range: -2.8780

Max Act: 2.0533. Min Act: -0.0000

Data Index: 1366908 (Python Code)

Max Activating Token Index: 270

Text #11

Max Range: 2.8780. Min Range: -2.8780

Max Act: 1.9320. Min Act: -0.0000

Data Index: 1401554 (Python Code)

Max Activating Token Index: 874

Text #12

Max Range: 2.8780. Min Range: -2.8780

Max Act: 2.0425. Min Act: -0.0000

Data Index: 1517211 (Python Code)

Max Activating Token Index: 955

Text #13

Max Range: 2.8780. Min Range: -2.8780

Max Act: 2.1591. Min Act: -0.0000

Data Index: 1434152 (Python Code)

Max Activating Token Index: 597

Text #14

Max Range: 2.8780. Min Range: -2.8780

Max Act: 2.2728. Min Act: -0.0000

Data Index: 1381933 (Python Code)

Max Activating Token Index: 826

Text #15

Max Range: 2.8780. Min Range: -2.8780

Max Act: 2.1274. Min Act: -0.0000

Data Index: 1501558 (Python Code)

Max Activating Token Index: 403

Text #16

Max Range: 2.8780. Min Range: -2.8780

Max Act: 1.8245. Min Act: -0.0000

Data Index: 1454237 (Python Code)

Max Activating Token Index: 934

Text #17

Max Range: 2.8780. Min Range: -2.8780

Max Act: 2.1345. Min Act: -0.0000

Data Index: 1584426 (Python Code)

Max Activating Token Index: 642

Text #18

Max Range: 2.8780. Min Range: -2.8780

Max Act: 2.0113. Min Act: -0.0000

Data Index: 1529286 (Python Code)

Max Activating Token Index: 899

Text #19

Max Range: 2.8780. Min Range: -2.8780

Max Act: 2.1387. Min Act: -0.0000

Data Index: 1640028 (Python Code)

Max Activating Token Index: 442