Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3702 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7268. Min Range: -1.7268

Max Act: 1.7268. Min Act: -0.0001

Data Index: 1536703 (Python Code)

Max Activating Token Index: 23

Text #1

Max Range: 1.7268. Min Range: -1.7268

Max Act: 1.6059. Min Act: -0.0001

Data Index: 1529741 (Python Code)

Max Activating Token Index: 43

Text #2

Max Range: 1.7268. Min Range: -1.7268

Max Act: 1.5563. Min Act: -0.0001

Data Index: 1572062 (Python Code)

Max Activating Token Index: 85

Text #3

Max Range: 1.7268. Min Range: -1.7268

Max Act: 1.5937. Min Act: -0.0001

Data Index: 1575508 (Python Code)

Max Activating Token Index: 168

Text #4

Max Range: 1.7268. Min Range: -1.7268

Max Act: 1.5987. Min Act: -0.0001

Data Index: 1647155 (Python Code)

Max Activating Token Index: 59

Text #5

Max Range: 1.7268. Min Range: -1.7268

Max Act: 1.5392. Min Act: -0.0001

Data Index: 1641771 (Python Code)

Max Activating Token Index: 88

Text #6

Max Range: 1.7268. Min Range: -1.7268

Max Act: 1.5069. Min Act: -0.0001

Data Index: 1459072 (Python Code)

Max Activating Token Index: 170

Text #7

Max Range: 1.7268. Min Range: -1.7268

Max Act: 1.5070. Min Act: -0.0001

Data Index: 1446337 (Python Code)

Max Activating Token Index: 87

Text #8

Max Range: 1.7268. Min Range: -1.7268

Max Act: 1.5068. Min Act: -0.0001

Data Index: 782572 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 1.7268. Min Range: -1.7268

Max Act: 1.5401. Min Act: -0.0001

Data Index: 1591893 (Python Code)

Max Activating Token Index: 53

Text #10

Max Range: 1.7268. Min Range: -1.7268

Max Act: 1.4480. Min Act: -0.0001

Data Index: 1490379 (Python Code)

Max Activating Token Index: 24

Text #11

Max Range: 1.7268. Min Range: -1.7268

Max Act: 1.4908. Min Act: -0.0001

Data Index: 1565942 (Python Code)

Max Activating Token Index: 27

Text #12

Max Range: 1.7268. Min Range: -1.7268

Max Act: 1.4830. Min Act: -0.0001

Data Index: 1398892 (Python Code)

Max Activating Token Index: 16

Text #13

Max Range: 1.7268. Min Range: -1.7268

Max Act: 1.3757. Min Act: -0.0001

Data Index: 1362748 (Python Code)

Max Activating Token Index: 75

Text #14

Max Range: 1.7268. Min Range: -1.7268

Max Act: 1.4533. Min Act: -0.0001

Data Index: 1562445 (Python Code)

Max Activating Token Index: 72

Text #15

Max Range: 1.7268. Min Range: -1.7268

Max Act: 1.4307. Min Act: -0.0001

Data Index: 1574591 (Python Code)

Max Activating Token Index: 63

Text #16

Max Range: 1.7268. Min Range: -1.7268

Max Act: 1.4305. Min Act: -0.0001

Data Index: 1439936 (Python Code)

Max Activating Token Index: 61

Text #17

Max Range: 1.7268. Min Range: -1.7268

Max Act: 1.4613. Min Act: -0.0001

Data Index: 1447867 (Python Code)

Max Activating Token Index: 27

Text #18

Max Range: 1.7268. Min Range: -1.7268

Max Act: 1.3752. Min Act: -0.0001

Data Index: 1533756 (Python Code)

Max Activating Token Index: 41

Text #19

Max Range: 1.7268. Min Range: -1.7268

Max Act: 1.3724. Min Act: -0.0001

Data Index: 1498586 (Python Code)

Max Activating Token Index: 42