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

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

Neuron 137 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0935. Min Range: -1.0935

Max Act: 1.0935. Min Act: -0.0001

Data Index: 1524679 (Python Code)

Max Activating Token Index: 824

Text #1

Max Range: 1.0935. Min Range: -1.0935

Max Act: 0.8763. Min Act: -0.0001

Data Index: 1431989 (Python Code)

Max Activating Token Index: 872

Text #2

Max Range: 1.0935. Min Range: -1.0935

Max Act: 0.9977. Min Act: -0.0001

Data Index: 1480486 (Python Code)

Max Activating Token Index: 869

Text #3

Max Range: 1.0935. Min Range: -1.0935

Max Act: 0.8284. Min Act: -0.0001

Data Index: 1490938 (Python Code)

Max Activating Token Index: 747

Text #4

Max Range: 1.0935. Min Range: -1.0935

Max Act: 0.8725. Min Act: -0.0001

Data Index: 1547726 (Python Code)

Max Activating Token Index: 491

Text #5

Max Range: 1.0935. Min Range: -1.0935

Max Act: 0.9050. Min Act: -0.0001

Data Index: 1603586 (Python Code)

Max Activating Token Index: 778

Text #6

Max Range: 1.0935. Min Range: -1.0935

Max Act: 1.0188. Min Act: -0.0001

Data Index: 1610193 (Python Code)

Max Activating Token Index: 863

Text #7

Max Range: 1.0935. Min Range: -1.0935

Max Act: 0.8675. Min Act: -0.0001

Data Index: 1502044 (Python Code)

Max Activating Token Index: 850

Text #8

Max Range: 1.0935. Min Range: -1.0935

Max Act: 0.8331. Min Act: -0.0001

Data Index: 1503883 (Python Code)

Max Activating Token Index: 876

Text #9

Max Range: 1.0935. Min Range: -1.0935

Max Act: 1.0275. Min Act: -0.0001

Data Index: 1632131 (Python Code)

Max Activating Token Index: 866

Text #10

Max Range: 1.0935. Min Range: -1.0935

Max Act: 0.9984. Min Act: -0.0001

Data Index: 1492488 (Python Code)

Max Activating Token Index: 810

Text #11

Max Range: 1.0935. Min Range: -1.0935

Max Act: 0.9613. Min Act: -0.0001

Data Index: 1512320 (Python Code)

Max Activating Token Index: 187

Text #12

Max Range: 1.0935. Min Range: -1.0935

Max Act: 0.8547. Min Act: -0.0001

Data Index: 1568306 (Python Code)

Max Activating Token Index: 830

Text #13

Max Range: 1.0935. Min Range: -1.0935

Max Act: 1.0543. Min Act: -0.0001

Data Index: 1506850 (Python Code)

Max Activating Token Index: 691

Text #14

Max Range: 1.0935. Min Range: -1.0935

Max Act: 0.7267. Min Act: -0.0001

Data Index: 1566214 (Python Code)

Max Activating Token Index: 855

Text #15

Max Range: 1.0935. Min Range: -1.0935

Max Act: 0.9656. Min Act: -0.0001

Data Index: 1405782 (Python Code)

Max Activating Token Index: 780

Text #16

Max Range: 1.0935. Min Range: -1.0935

Max Act: 0.9518. Min Act: -0.0001

Data Index: 1645157 (Python Code)

Max Activating Token Index: 768

Text #17

Max Range: 1.0935. Min Range: -1.0935

Max Act: 0.9483. Min Act: -0.0001

Data Index: 1603687 (Python Code)

Max Activating Token Index: 85

Text #18

Max Range: 1.0935. Min Range: -1.0935

Max Act: 0.9406. Min Act: -0.0001

Data Index: 1023837 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 1.0935. Min Range: -1.0935

Max Act: 1.0489. Min Act: -0.0001

Data Index: 1531204 (Python Code)

Max Activating Token Index: 856