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

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

Neuron 2306 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: 0.1048. Min Range: -0.1048

Max Act: 0.1048. Min Act: -0.0002

Data Index: 552702 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.1000. Min Act: -0.0002

Data Index: 1562364 (Python Code)

Max Activating Token Index: 705

Text #2

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.1008. Min Act: -0.0002

Data Index: 1238354 (C4 (Web Text))

Max Activating Token Index: 591

Text #3

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0949. Min Act: -0.0002

Data Index: 280103 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0953. Min Act: -0.0002

Data Index: 1111160 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0892. Min Act: -0.0002

Data Index: 467466 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0892. Min Act: -0.0002

Data Index: 366588 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0880. Min Act: -0.0002

Data Index: 1397375 (Python Code)

Max Activating Token Index: 19

Text #8

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0867. Min Act: -0.0002

Data Index: 1354048 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0872. Min Act: -0.0002

Data Index: 1443137 (Python Code)

Max Activating Token Index: 19

Text #10

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0856. Min Act: -0.0002

Data Index: 1619902 (Python Code)

Max Activating Token Index: 8

Text #11

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0856. Min Act: -0.0002

Data Index: 1613733 (Python Code)

Max Activating Token Index: 67

Text #12

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0831. Min Act: -0.0002

Data Index: 1640726 (Python Code)

Max Activating Token Index: 39

Text #13

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0845. Min Act: -0.0002

Data Index: 1397448 (Python Code)

Max Activating Token Index: 652

Text #14

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0838. Min Act: -0.0002

Data Index: 1584048 (Python Code)

Max Activating Token Index: 31

Text #15

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0826. Min Act: -0.0002

Data Index: 718681 (C4 (Web Text))

Max Activating Token Index: 603

Text #16

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0822. Min Act: -0.0002

Data Index: 1619645 (Python Code)

Max Activating Token Index: 777

Text #17

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0833. Min Act: -0.0002

Data Index: 1401499 (Python Code)

Max Activating Token Index: 825

Text #18

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0810. Min Act: -0.0002

Data Index: 1236354 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 0.1048. Min Range: -0.1048

Max Act: 0.0821. Min Act: -0.0002

Data Index: 1527626 (Python Code)

Max Activating Token Index: 40