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

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

Neuron 6132 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: 0.0870. Min Range: -0.0870

Max Act: 0.0870. Min Act: -0.0002

Data Index: 1446301 (Python Code)

Max Activating Token Index: 788

Text #1

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0853. Min Act: -0.0002

Data Index: 1163398 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0848. Min Act: -0.0002

Data Index: 1411903 (Python Code)

Max Activating Token Index: 113

Text #3

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0831. Min Act: -0.0002

Data Index: 1124427 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0845. Min Act: -0.0002

Data Index: 1383128 (Python Code)

Max Activating Token Index: 312

Text #5

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0827. Min Act: -0.0002

Data Index: 931464 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0835. Min Act: -0.0002

Data Index: 1396434 (Python Code)

Max Activating Token Index: 14

Text #7

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0837. Min Act: -0.0002

Data Index: 1156474 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0832. Min Act: -0.0002

Data Index: 944855 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0817. Min Act: -0.0002

Data Index: 1382843 (Python Code)

Max Activating Token Index: 244

Text #10

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0805. Min Act: -0.0002

Data Index: 1438404 (Python Code)

Max Activating Token Index: 803

Text #11

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0816. Min Act: -0.0002

Data Index: 1627408 (Python Code)

Max Activating Token Index: 525

Text #12

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0804. Min Act: -0.0002

Data Index: 1591213 (Python Code)

Max Activating Token Index: 342

Text #13

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0798. Min Act: -0.0002

Data Index: 1531228 (Python Code)

Max Activating Token Index: 531

Text #14

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0792. Min Act: -0.0002

Data Index: 925336 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0808. Min Act: -0.0002

Data Index: 1234014 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0801. Min Act: -0.0002

Data Index: 1548131 (Python Code)

Max Activating Token Index: 302

Text #17

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0788. Min Act: -0.0002

Data Index: 1530646 (Python Code)

Max Activating Token Index: 807

Text #18

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0779. Min Act: -0.0002

Data Index: 1420489 (Python Code)

Max Activating Token Index: 66

Text #19

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0775. Min Act: -0.0002

Data Index: 1551257 (Python Code)

Max Activating Token Index: 214