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

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

Neuron 4126 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: 0.1957. Min Range: -0.1957

Max Act: 0.1943. Min Act: -0.0002

Data Index: 1575259 (Python Code)

Max Activating Token Index: 259

Text #1

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1949. Min Act: -0.0002

Data Index: 730317 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1957. Min Act: -0.0002

Data Index: 1379363 (Python Code)

Max Activating Token Index: 288

Text #3

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1922. Min Act: -0.0002

Data Index: 1617288 (Python Code)

Max Activating Token Index: 510

Text #4

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1870. Min Act: -0.0002

Data Index: 1632935 (Python Code)

Max Activating Token Index: 836

Text #5

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1829. Min Act: -0.0002

Data Index: 1255677 (C4 (Web Text))

Max Activating Token Index: 866

Text #6

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1814. Min Act: -0.0002

Data Index: 1411228 (Python Code)

Max Activating Token Index: 436

Text #7

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1816. Min Act: -0.0002

Data Index: 1400744 (Python Code)

Max Activating Token Index: 545

Text #8

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1740. Min Act: -0.0002

Data Index: 678599 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1758. Min Act: -0.0002

Data Index: 1023418 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1721. Min Act: -0.0002

Data Index: 1433828 (Python Code)

Max Activating Token Index: 505

Text #11

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1691. Min Act: -0.0002

Data Index: 1634227 (Python Code)

Max Activating Token Index: 66

Text #12

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1626. Min Act: -0.0002

Data Index: 1513927 (Python Code)

Max Activating Token Index: 50

Text #13

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1644. Min Act: -0.0002

Data Index: 1378109 (Python Code)

Max Activating Token Index: 790

Text #14

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1552. Min Act: -0.0002

Data Index: 1598917 (Python Code)

Max Activating Token Index: 332

Text #15

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1573. Min Act: -0.0002

Data Index: 1601625 (Python Code)

Max Activating Token Index: 720

Text #16

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1578. Min Act: -0.0002

Data Index: 1561986 (Python Code)

Max Activating Token Index: 168

Text #17

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1538. Min Act: -0.0002

Data Index: 1421019 (Python Code)

Max Activating Token Index: 192

Text #18

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1520. Min Act: -0.0002

Data Index: 1649322 (Python Code)

Max Activating Token Index: 592

Text #19

Max Range: 0.1957. Min Range: -0.1957

Max Act: 0.1525. Min Act: -0.0002

Data Index: 1517603 (Python Code)

Max Activating Token Index: 667