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

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

Neuron 940 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: 2.5637. Min Range: -2.5637

Max Act: 2.5637. Min Act: 0.0000

Data Index: 1391036 (Python Code)

Max Activating Token Index: 706

Text #1

Max Range: 2.5637. Min Range: -2.5637

Max Act: 2.1066. Min Act: -0.0000

Data Index: 1634037 (Python Code)

Max Activating Token Index: 911

Text #2

Max Range: 2.5637. Min Range: -2.5637

Max Act: 2.0505. Min Act: -0.0000

Data Index: 1529739 (Python Code)

Max Activating Token Index: 778

Text #3

Max Range: 2.5637. Min Range: -2.5637

Max Act: 1.9426. Min Act: 0.0000

Data Index: 1624282 (Python Code)

Max Activating Token Index: 501

Text #4

Max Range: 2.5637. Min Range: -2.5637

Max Act: 1.9349. Min Act: 0.0000

Data Index: 1360942 (Python Code)

Max Activating Token Index: 877

Text #5

Max Range: 2.5637. Min Range: -2.5637

Max Act: 1.7639. Min Act: 0.0000

Data Index: 1454788 (Python Code)

Max Activating Token Index: 733

Text #6

Max Range: 2.5637. Min Range: -2.5637

Max Act: 1.7461. Min Act: -0.0000

Data Index: 1383337 (Python Code)

Max Activating Token Index: 90

Text #7

Max Range: 2.5637. Min Range: -2.5637

Max Act: 1.7393. Min Act: -0.0000

Data Index: 1377949 (Python Code)

Max Activating Token Index: 228

Text #8

Max Range: 2.5637. Min Range: -2.5637

Max Act: 1.7492. Min Act: -0.0000

Data Index: 1443835 (Python Code)

Max Activating Token Index: 273

Text #9

Max Range: 2.5637. Min Range: -2.5637

Max Act: 1.7878. Min Act: -0.0000

Data Index: 1457936 (Python Code)

Max Activating Token Index: 218

Text #10

Max Range: 2.5637. Min Range: -2.5637

Max Act: 1.6636. Min Act: -0.0000

Data Index: 1650255 (Python Code)

Max Activating Token Index: 63

Text #11

Max Range: 2.5637. Min Range: -2.5637

Max Act: 1.6842. Min Act: -0.0000

Data Index: 1483227 (Python Code)

Max Activating Token Index: 877

Text #12

Max Range: 2.5637. Min Range: -2.5637

Max Act: 1.5331. Min Act: -0.0000

Data Index: 1644008 (Python Code)

Max Activating Token Index: 150

Text #13

Max Range: 2.5637. Min Range: -2.5637

Max Act: 1.5359. Min Act: -0.0000

Data Index: 1619977 (Python Code)

Max Activating Token Index: 675

Text #14

Max Range: 2.5637. Min Range: -2.5637

Max Act: 1.6187. Min Act: -0.0000

Data Index: 1564065 (Python Code)

Max Activating Token Index: 770

Text #15

Max Range: 2.5637. Min Range: -2.5637

Max Act: 1.5044. Min Act: 0.0000

Data Index: 1635745 (Python Code)

Max Activating Token Index: 854

Text #16

Max Range: 2.5637. Min Range: -2.5637

Max Act: 1.3968. Min Act: -0.0000

Data Index: 1600966 (Python Code)

Max Activating Token Index: 654

Text #17

Max Range: 2.5637. Min Range: -2.5637

Max Act: 1.3858. Min Act: -0.0000

Data Index: 1481661 (Python Code)

Max Activating Token Index: 226

Text #18

Max Range: 2.5637. Min Range: -2.5637

Max Act: 1.5477. Min Act: -0.0000

Data Index: 1441815 (Python Code)

Max Activating Token Index: 712

Text #19

Max Range: 2.5637. Min Range: -2.5637

Max Act: 1.4626. Min Act: -0.0000

Data Index: 1523476 (Python Code)

Max Activating Token Index: 168