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

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

Neuron 2166 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: 1.4849. Min Range: -1.4849

Max Act: 1.4849. Min Act: -0.0002

Data Index: 1629962 (Python Code)

Max Activating Token Index: 811

Text #1

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.3357. Min Act: -0.0002

Data Index: 1602248 (Python Code)

Max Activating Token Index: 750

Text #2

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.3233. Min Act: -0.0002

Data Index: 1158330 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.1770. Min Act: -0.0002

Data Index: 415801 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.1670. Min Act: -0.0002

Data Index: 1643597 (Python Code)

Max Activating Token Index: 759

Text #5

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.1787. Min Act: -0.0002

Data Index: 1434256 (Python Code)

Max Activating Token Index: 15

Text #6

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.1835. Min Act: -0.0002

Data Index: 741355 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.2180. Min Act: -0.0002

Data Index: 1560353 (Python Code)

Max Activating Token Index: 773

Text #8

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.1697. Min Act: -0.0002

Data Index: 1420106 (Python Code)

Max Activating Token Index: 924

Text #9

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.1577. Min Act: -0.0002

Data Index: 879746 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.1969. Min Act: -0.0002

Data Index: 1520544 (Python Code)

Max Activating Token Index: 20

Text #11

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.1746. Min Act: -0.0002

Data Index: 1403840 (Python Code)

Max Activating Token Index: 80

Text #12

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.1748. Min Act: -0.0002

Data Index: 1408201 (Python Code)

Max Activating Token Index: 10

Text #13

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.1607. Min Act: -0.0002

Data Index: 842630 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.1157. Min Act: -0.0002

Data Index: 29976 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.1047. Min Act: -0.0002

Data Index: 468738 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.0835. Min Act: -0.0002

Data Index: 1462291 (Python Code)

Max Activating Token Index: 760

Text #17

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.1001. Min Act: -0.0002

Data Index: 1400869 (Python Code)

Max Activating Token Index: 589

Text #18

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.1042. Min Act: -0.0002

Data Index: 1502860 (Python Code)

Max Activating Token Index: 312

Text #19

Max Range: 1.4849. Min Range: -1.4849

Max Act: 1.0905. Min Act: -0.0002

Data Index: 1381662 (Python Code)

Max Activating Token Index: 955