Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 665 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.4389. Min Act: -0.0001

Data Index: 1382729 (Python Code)

Max Activating Token Index: 38

Text #1

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.4384. Min Act: -0.0001

Data Index: 1526835 (Python Code)

Max Activating Token Index: 35

Text #2

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.4227. Min Act: -0.0001

Data Index: 1556313 (Python Code)

Max Activating Token Index: 9

Text #3

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.4230. Min Act: -0.0001

Data Index: 1490931 (Python Code)

Max Activating Token Index: 21

Text #4

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.4225. Min Act: -0.0001

Data Index: 1589828 (Python Code)

Max Activating Token Index: 10

Text #5

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.4182. Min Act: -0.0001

Data Index: 1389271 (Python Code)

Max Activating Token Index: 15

Text #6

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.4300. Min Act: -0.0001

Data Index: 1491287 (Python Code)

Max Activating Token Index: 37

Text #7

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.3958. Min Act: -0.0001

Data Index: 1647727 (Python Code)

Max Activating Token Index: 26

Text #8

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.3946. Min Act: -0.0001

Data Index: 1555463 (Python Code)

Max Activating Token Index: 8

Text #9

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.3820. Min Act: -0.0001

Data Index: 1437372 (Python Code)

Max Activating Token Index: 37

Text #10

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.3708. Min Act: -0.0001

Data Index: 1377255 (Python Code)

Max Activating Token Index: 24

Text #11

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.3340. Min Act: -0.0001

Data Index: 1580863 (Python Code)

Max Activating Token Index: 19

Text #12

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.3168. Min Act: -0.0001

Data Index: 1362845 (Python Code)

Max Activating Token Index: 84

Text #13

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.3120. Min Act: -0.0001

Data Index: 1504884 (Python Code)

Max Activating Token Index: 58

Text #14

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.2954. Min Act: -0.0001

Data Index: 1479005 (Python Code)

Max Activating Token Index: 375

Text #15

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.2797. Min Act: -0.0001

Data Index: 1599153 (Python Code)

Max Activating Token Index: 36

Text #16

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.2842. Min Act: -0.0001

Data Index: 1632071 (Python Code)

Max Activating Token Index: 53

Text #17

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.2633. Min Act: -0.0001

Data Index: 1373956 (Python Code)

Max Activating Token Index: 104

Text #18

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.2515. Min Act: -0.0001

Data Index: 1627894 (Python Code)

Max Activating Token Index: 35

Text #19

Max Range: 0.4389. Min Range: -0.4389

Max Act: 0.2470. Min Act: -0.0001

Data Index: 1395801 (Python Code)

Max Activating Token Index: 607