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

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

Neuron 4227 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: 0.1056. Min Range: -0.1056

Max Act: 0.1056. Min Act: -0.0002

Data Index: 1448970 (Python Code)

Max Activating Token Index: 131

Text #1

Max Range: 0.1056. Min Range: -0.1056

Max Act: 0.1032. Min Act: -0.0002

Data Index: 1457933 (Python Code)

Max Activating Token Index: 360

Text #2

Max Range: 0.1056. Min Range: -0.1056

Max Act: 0.1046. Min Act: -0.0002

Data Index: 1643864 (Python Code)

Max Activating Token Index: 147

Text #3

Max Range: 0.1056. Min Range: -0.1056

Max Act: 0.1025. Min Act: -0.0002

Data Index: 1525745 (Python Code)

Max Activating Token Index: 302

Text #4

Max Range: 0.1056. Min Range: -0.1056

Max Act: 0.1001. Min Act: -0.0002

Data Index: 1453512 (Python Code)

Max Activating Token Index: 887

Text #5

Max Range: 0.1056. Min Range: -0.1056

Max Act: 0.0919. Min Act: -0.0002

Data Index: 1390559 (Python Code)

Max Activating Token Index: 483

Text #6

Max Range: 0.1056. Min Range: -0.1056

Max Act: 0.0903. Min Act: -0.0002

Data Index: 1588643 (Python Code)

Max Activating Token Index: 767

Text #7

Max Range: 0.1056. Min Range: -0.1056

Max Act: 0.0888. Min Act: -0.0002

Data Index: 1533259 (Python Code)

Max Activating Token Index: 150

Text #8

Max Range: 0.1056. Min Range: -0.1056

Max Act: 0.0896. Min Act: -0.0002

Data Index: 1406342 (Python Code)

Max Activating Token Index: 604

Text #9

Max Range: 0.1056. Min Range: -0.1056

Max Act: 0.0884. Min Act: -0.0002

Data Index: 1381858 (Python Code)

Max Activating Token Index: 168

Text #10

Max Range: 0.1056. Min Range: -0.1056

Max Act: 0.0878. Min Act: -0.0002

Data Index: 1498372 (Python Code)

Max Activating Token Index: 643

Text #11

Max Range: 0.1056. Min Range: -0.1056

Max Act: 0.0835. Min Act: -0.0002

Data Index: 1468440 (Python Code)

Max Activating Token Index: 612

Text #12

Max Range: 0.1056. Min Range: -0.1056

Max Act: 0.0835. Min Act: -0.0002

Data Index: 1498607 (Python Code)

Max Activating Token Index: 518

Text #13

Max Range: 0.1056. Min Range: -0.1056

Max Act: 0.0837. Min Act: -0.0002

Data Index: 1586737 (Python Code)

Max Activating Token Index: 517

Text #14

Max Range: 0.1056. Min Range: -0.1056

Max Act: 0.0832. Min Act: -0.0002

Data Index: 1655480 (Python Code)

Max Activating Token Index: 538

Text #15

Max Range: 0.1056. Min Range: -0.1056

Max Act: 0.0831. Min Act: -0.0002

Data Index: 1536476 (Python Code)

Max Activating Token Index: 526

Text #16

Max Range: 0.1056. Min Range: -0.1056

Max Act: 0.0772. Min Act: -0.0002

Data Index: 1528718 (Python Code)

Max Activating Token Index: 911

Text #17

Max Range: 0.1056. Min Range: -0.1056

Max Act: 0.0738. Min Act: -0.0002

Data Index: 455742 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 0.1056. Min Range: -0.1056

Max Act: 0.0718. Min Act: -0.0002

Data Index: 1626373 (Python Code)

Max Activating Token Index: 951

Text #19

Max Range: 0.1056. Min Range: -0.1056

Max Act: 0.0718. Min Act: -0.0002

Data Index: 1651655 (Python Code)

Max Activating Token Index: 621