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

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

Neuron 2631 in Layer 0

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: 1.0758. Min Range: -1.0758

Max Act: 1.0758. Min Act: -0.0001

Data Index: 1445088 (Python Code)

Max Activating Token Index: 853

Text #1

Max Range: 1.0758. Min Range: -1.0758

Max Act: 1.0555. Min Act: -0.0001

Data Index: 1527813 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 1.0758. Min Range: -1.0758

Max Act: 1.0054. Min Act: -0.0001

Data Index: 1392642 (Python Code)

Max Activating Token Index: 75

Text #3

Max Range: 1.0758. Min Range: -1.0758

Max Act: 1.0022. Min Act: -0.0001

Data Index: 1491802 (Python Code)

Max Activating Token Index: 148

Text #4

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.9914. Min Act: -0.0001

Data Index: 1366728 (Python Code)

Max Activating Token Index: 104

Text #5

Max Range: 1.0758. Min Range: -1.0758

Max Act: 1.0077. Min Act: -0.0001

Data Index: 1597555 (Python Code)

Max Activating Token Index: 164

Text #6

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.9913. Min Act: -0.0001

Data Index: 1575634 (Python Code)

Max Activating Token Index: 53

Text #7

Max Range: 1.0758. Min Range: -1.0758

Max Act: 1.0091. Min Act: -0.0001

Data Index: 1508258 (Python Code)

Max Activating Token Index: 196

Text #8

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.9773. Min Act: -0.0001

Data Index: 1637215 (Python Code)

Max Activating Token Index: 173

Text #9

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.9767. Min Act: -0.0001

Data Index: 1608359 (Python Code)

Max Activating Token Index: 621

Text #10

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.9752. Min Act: -0.0001

Data Index: 1626719 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.9759. Min Act: -0.0001

Data Index: 1455129 (Python Code)

Max Activating Token Index: 83

Text #12

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.9705. Min Act: -0.0001

Data Index: 1528466 (Python Code)

Max Activating Token Index: 29

Text #13

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.9728. Min Act: -0.0001

Data Index: 1641695 (Python Code)

Max Activating Token Index: 286

Text #14

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.9525. Min Act: -0.0001

Data Index: 1490768 (Python Code)

Max Activating Token Index: 413

Text #15

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.9718. Min Act: -0.0001

Data Index: 1615717 (Python Code)

Max Activating Token Index: 50

Text #16

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.9650. Min Act: -0.0001

Data Index: 1516729 (Python Code)

Max Activating Token Index: 93

Text #17

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.9501. Min Act: -0.0001

Data Index: 1655872 (Python Code)

Max Activating Token Index: 19

Text #18

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.9508. Min Act: -0.0001

Data Index: 1364759 (Python Code)

Max Activating Token Index: 40

Text #19

Max Range: 1.0758. Min Range: -1.0758

Max Act: 0.9665. Min Act: -0.0001

Data Index: 1428008 (Python Code)

Max Activating Token Index: 168