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

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

Neuron 5982 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8549. Min Range: -2.8549

Max Act: 2.8549. Min Act: -0.0000

Data Index: 24078 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 2.8549. Min Range: -2.8549

Max Act: 2.3642. Min Act: -0.0001

Data Index: 1523265 (Python Code)

Max Activating Token Index: 12

Text #2

Max Range: 2.8549. Min Range: -2.8549

Max Act: 2.2410. Min Act: -0.0001

Data Index: 436242 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 2.8549. Min Range: -2.8549

Max Act: 2.1857. Min Act: -0.0000

Data Index: 988837 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 2.8549. Min Range: -2.8549

Max Act: 2.0072. Min Act: -0.0000

Data Index: 399339 (C4 (Web Text))

Max Activating Token Index: 934

Text #5

Max Range: 2.8549. Min Range: -2.8549

Max Act: 2.2093. Min Act: -0.0001

Data Index: 186757 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 2.8549. Min Range: -2.8549

Max Act: 2.1553. Min Act: -0.0000

Data Index: 76902 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 2.8549. Min Range: -2.8549

Max Act: 2.0131. Min Act: -0.0001

Data Index: 1013601 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 2.8549. Min Range: -2.8549

Max Act: 1.9888. Min Act: -0.0000

Data Index: 1276882 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 2.8549. Min Range: -2.8549

Max Act: 2.1158. Min Act: -0.0000

Data Index: 913117 (C4 (Web Text))

Max Activating Token Index: 983

Text #10

Max Range: 2.8549. Min Range: -2.8549

Max Act: 1.9700. Min Act: -0.0001

Data Index: 1417916 (Python Code)

Max Activating Token Index: 596

Text #11

Max Range: 2.8549. Min Range: -2.8549

Max Act: 1.8614. Min Act: -0.0001

Data Index: 602445 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 2.8549. Min Range: -2.8549

Max Act: 2.0073. Min Act: -0.0000

Data Index: 834353 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 2.8549. Min Range: -2.8549

Max Act: 1.9138. Min Act: -0.0001

Data Index: 1376451 (Python Code)

Max Activating Token Index: 796

Text #14

Max Range: 2.8549. Min Range: -2.8549

Max Act: 1.8917. Min Act: -0.0001

Data Index: 1430623 (Python Code)

Max Activating Token Index: 583

Text #15

Max Range: 2.8549. Min Range: -2.8549

Max Act: 1.8748. Min Act: -0.0000

Data Index: 216730 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 2.8549. Min Range: -2.8549

Max Act: 1.8712. Min Act: -0.0001

Data Index: 1645336 (Python Code)

Max Activating Token Index: 991

Text #17

Max Range: 2.8549. Min Range: -2.8549

Max Act: 1.7559. Min Act: -0.0000

Data Index: 1636760 (Python Code)

Max Activating Token Index: 65

Text #18

Max Range: 2.8549. Min Range: -2.8549

Max Act: 1.8357. Min Act: -0.0000

Data Index: 1037433 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 2.8549. Min Range: -2.8549

Max Act: 1.8319. Min Act: -0.0000

Data Index: 293869 (C4 (Web Text))

Max Activating Token Index: 497