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

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

Neuron 3181 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.1563. Min Act: -0.0002

Data Index: 1539682 (Python Code)

Max Activating Token Index: 14

Text #1

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.1262. Min Act: -0.0002

Data Index: 1447324 (Python Code)

Max Activating Token Index: 378

Text #2

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.1420. Min Act: -0.0002

Data Index: 1446155 (Python Code)

Max Activating Token Index: 8

Text #3

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.1329. Min Act: -0.0002

Data Index: 1491649 (Python Code)

Max Activating Token Index: 487

Text #4

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.0697. Min Act: -0.0002

Data Index: 1367976 (Python Code)

Max Activating Token Index: 552

Text #5

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.0599. Min Act: -0.0002

Data Index: 1654480 (Python Code)

Max Activating Token Index: 125

Text #6

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.0577. Min Act: -0.0002

Data Index: 962014 (C4 (Web Text))

Max Activating Token Index: 782

Text #7

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.0173. Min Act: -0.0002

Data Index: 523642 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.0387. Min Act: -0.0002

Data Index: 559507 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.0241. Min Act: -0.0002

Data Index: 932834 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9991. Min Act: -0.0002

Data Index: 1404521 (Python Code)

Max Activating Token Index: 86

Text #11

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.0092. Min Act: -0.0002

Data Index: 1364114 (Python Code)

Max Activating Token Index: 295

Text #12

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.0077. Min Act: -0.0002

Data Index: 1550733 (Python Code)

Max Activating Token Index: 132

Text #13

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.0081. Min Act: -0.0002

Data Index: 1433943 (Python Code)

Max Activating Token Index: 402

Text #14

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9972. Min Act: -0.0002

Data Index: 1522158 (Python Code)

Max Activating Token Index: 528

Text #15

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.0064. Min Act: -0.0002

Data Index: 1550976 (Python Code)

Max Activating Token Index: 983

Text #16

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.0126. Min Act: -0.0002

Data Index: 1372400 (Python Code)

Max Activating Token Index: 153

Text #17

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.0005. Min Act: -0.0002

Data Index: 1402795 (Python Code)

Max Activating Token Index: 159

Text #18

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.0010. Min Act: -0.0002

Data Index: 1554733 (Python Code)

Max Activating Token Index: 204

Text #19

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9831. Min Act: -0.0002

Data Index: 1638814 (Python Code)

Max Activating Token Index: 413