Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3442 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0601. Min Act: -0.0002

Data Index: 1595823 (Python Code)

Max Activating Token Index: 35

Text #1

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0590. Min Act: -0.0002

Data Index: 1625170 (Python Code)

Max Activating Token Index: 63

Text #2

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0583. Min Act: -0.0002

Data Index: 1514026 (Python Code)

Max Activating Token Index: 37

Text #3

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0581. Min Act: -0.0002

Data Index: 1472236 (Python Code)

Max Activating Token Index: 41

Text #4

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0561. Min Act: -0.0002

Data Index: 1507657 (Python Code)

Max Activating Token Index: 55

Text #5

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0553. Min Act: -0.0002

Data Index: 1492170 (Python Code)

Max Activating Token Index: 51

Text #6

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0553. Min Act: -0.0002

Data Index: 1624522 (Python Code)

Max Activating Token Index: 45

Text #7

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0543. Min Act: -0.0002

Data Index: 1386976 (Python Code)

Max Activating Token Index: 96

Text #8

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0559. Min Act: -0.0002

Data Index: 1530461 (Python Code)

Max Activating Token Index: 19

Text #9

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0534. Min Act: -0.0002

Data Index: 1649116 (Python Code)

Max Activating Token Index: 14

Text #10

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0512. Min Act: -0.0002

Data Index: 1444407 (Python Code)

Max Activating Token Index: 6

Text #11

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0529. Min Act: -0.0002

Data Index: 1617309 (Python Code)

Max Activating Token Index: 52

Text #12

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0529. Min Act: -0.0002

Data Index: 1373930 (Python Code)

Max Activating Token Index: 61

Text #13

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0518. Min Act: -0.0002

Data Index: 1612299 (Python Code)

Max Activating Token Index: 19

Text #14

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0527. Min Act: -0.0002

Data Index: 1402654 (Python Code)

Max Activating Token Index: 42

Text #15

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0527. Min Act: -0.0002

Data Index: 1393475 (Python Code)

Max Activating Token Index: 42

Text #16

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0527. Min Act: -0.0002

Data Index: 1592861 (Python Code)

Max Activating Token Index: 45

Text #17

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0526. Min Act: -0.0002

Data Index: 1463782 (Python Code)

Max Activating Token Index: 61

Text #18

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0525. Min Act: -0.0002

Data Index: 1504361 (Python Code)

Max Activating Token Index: 82

Text #19

Max Range: 0.0601. Min Range: -0.0601

Max Act: 0.0524. Min Act: -0.0002

Data Index: 1603373 (Python Code)

Max Activating Token Index: 38