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

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

Neuron 2220 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: 0.6643. Min Range: -0.6643

Max Act: 0.6643. Min Act: -0.0002

Data Index: 1399235 (Python Code)

Max Activating Token Index: 202

Text #1

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.6205. Min Act: -0.0002

Data Index: 1406765 (Python Code)

Max Activating Token Index: 7

Text #2

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.6127. Min Act: -0.0002

Data Index: 1525557 (Python Code)

Max Activating Token Index: 3

Text #3

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.6127. Min Act: -0.0002

Data Index: 1405871 (Python Code)

Max Activating Token Index: 3

Text #4

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.6127. Min Act: -0.0002

Data Index: 1654741 (Python Code)

Max Activating Token Index: 3

Text #5

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.6240. Min Act: -0.0002

Data Index: 1606845 (Python Code)

Max Activating Token Index: 730

Text #6

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.6144. Min Act: -0.0002

Data Index: 1420748 (Python Code)

Max Activating Token Index: 854

Text #7

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5973. Min Act: -0.0002

Data Index: 1402421 (Python Code)

Max Activating Token Index: 338

Text #8

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5901. Min Act: -0.0002

Data Index: 1483476 (Python Code)

Max Activating Token Index: 761

Text #9

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5904. Min Act: -0.0002

Data Index: 1626969 (Python Code)

Max Activating Token Index: 73

Text #10

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5856. Min Act: -0.0002

Data Index: 1631068 (Python Code)

Max Activating Token Index: 300

Text #11

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5850. Min Act: -0.0002

Data Index: 1387436 (Python Code)

Max Activating Token Index: 5

Text #12

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5967. Min Act: -0.0002

Data Index: 1471945 (Python Code)

Max Activating Token Index: 374

Text #13

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5867. Min Act: -0.0002

Data Index: 1627379 (Python Code)

Max Activating Token Index: 392

Text #14

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5946. Min Act: -0.0002

Data Index: 1634401 (Python Code)

Max Activating Token Index: 8

Text #15

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5860. Min Act: -0.0002

Data Index: 1616309 (Python Code)

Max Activating Token Index: 79

Text #16

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5860. Min Act: -0.0002

Data Index: 1520209 (Python Code)

Max Activating Token Index: 622

Text #17

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5748. Min Act: -0.0002

Data Index: 1480053 (Python Code)

Max Activating Token Index: 8

Text #18

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5728. Min Act: -0.0002

Data Index: 1469486 (Python Code)

Max Activating Token Index: 303

Text #19

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5828. Min Act: -0.0002

Data Index: 1626043 (Python Code)

Max Activating Token Index: 607