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

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

Neuron 709 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: 1.1869. Min Range: -1.1869

Max Act: 1.1869. Min Act: -0.0002

Data Index: 1473244 (Python Code)

Max Activating Token Index: 135

Text #1

Max Range: 1.1869. Min Range: -1.1869

Max Act: 1.1472. Min Act: -0.0002

Data Index: 1373112 (Python Code)

Max Activating Token Index: 324

Text #2

Max Range: 1.1869. Min Range: -1.1869

Max Act: 1.0927. Min Act: -0.0002

Data Index: 1650867 (Python Code)

Max Activating Token Index: 620

Text #3

Max Range: 1.1869. Min Range: -1.1869

Max Act: 1.0701. Min Act: -0.0002

Data Index: 1622582 (Python Code)

Max Activating Token Index: 393

Text #4

Max Range: 1.1869. Min Range: -1.1869

Max Act: 1.0754. Min Act: -0.0002

Data Index: 1467743 (Python Code)

Max Activating Token Index: 154

Text #5

Max Range: 1.1869. Min Range: -1.1869

Max Act: 1.0657. Min Act: -0.0002

Data Index: 1566445 (Python Code)

Max Activating Token Index: 114

Text #6

Max Range: 1.1869. Min Range: -1.1869

Max Act: 1.0479. Min Act: -0.0002

Data Index: 1508053 (Python Code)

Max Activating Token Index: 293

Text #7

Max Range: 1.1869. Min Range: -1.1869

Max Act: 1.0409. Min Act: -0.0002

Data Index: 1488469 (Python Code)

Max Activating Token Index: 241

Text #8

Max Range: 1.1869. Min Range: -1.1869

Max Act: 1.0258. Min Act: -0.0002

Data Index: 1632674 (Python Code)

Max Activating Token Index: 167

Text #9

Max Range: 1.1869. Min Range: -1.1869

Max Act: 1.0171. Min Act: -0.0002

Data Index: 1533505 (Python Code)

Max Activating Token Index: 361

Text #10

Max Range: 1.1869. Min Range: -1.1869

Max Act: 1.0001. Min Act: -0.0002

Data Index: 1575862 (Python Code)

Max Activating Token Index: 247

Text #11

Max Range: 1.1869. Min Range: -1.1869

Max Act: 1.0227. Min Act: -0.0002

Data Index: 1647479 (Python Code)

Max Activating Token Index: 189

Text #12

Max Range: 1.1869. Min Range: -1.1869

Max Act: 1.0000. Min Act: -0.0002

Data Index: 1526009 (Python Code)

Max Activating Token Index: 333

Text #13

Max Range: 1.1869. Min Range: -1.1869

Max Act: 0.9954. Min Act: -0.0002

Data Index: 1544221 (Python Code)

Max Activating Token Index: 305

Text #14

Max Range: 1.1869. Min Range: -1.1869

Max Act: 0.9911. Min Act: -0.0002

Data Index: 1411229 (Python Code)

Max Activating Token Index: 151

Text #15

Max Range: 1.1869. Min Range: -1.1869

Max Act: 0.9825. Min Act: -0.0002

Data Index: 1435493 (Python Code)

Max Activating Token Index: 106

Text #16

Max Range: 1.1869. Min Range: -1.1869

Max Act: 0.9586. Min Act: -0.0002

Data Index: 1530096 (Python Code)

Max Activating Token Index: 119

Text #17

Max Range: 1.1869. Min Range: -1.1869

Max Act: 0.9618. Min Act: -0.0002

Data Index: 1517466 (Python Code)

Max Activating Token Index: 369

Text #18

Max Range: 1.1869. Min Range: -1.1869

Max Act: 0.9699. Min Act: -0.0002

Data Index: 1524250 (Python Code)

Max Activating Token Index: 97

Text #19

Max Range: 1.1869. Min Range: -1.1869

Max Act: 0.9434. Min Act: -0.0002

Data Index: 1526620 (Python Code)

Max Activating Token Index: 334