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

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

Neuron 5883 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4438. Min Range: -1.4438

Max Act: 1.4299. Min Act: -0.0000

Data Index: 1523392 (Python Code)

Max Activating Token Index: 150

Text #1

Max Range: 1.4438. Min Range: -1.4438

Max Act: 1.4438. Min Act: -0.0000

Data Index: 1614937 (Python Code)

Max Activating Token Index: 151

Text #2

Max Range: 1.4438. Min Range: -1.4438

Max Act: 1.3910. Min Act: -0.0000

Data Index: 1496580 (Python Code)

Max Activating Token Index: 248

Text #3

Max Range: 1.4438. Min Range: -1.4438

Max Act: 1.3903. Min Act: -0.0000

Data Index: 1454715 (Python Code)

Max Activating Token Index: 48

Text #4

Max Range: 1.4438. Min Range: -1.4438

Max Act: 1.3359. Min Act: -0.0000

Data Index: 1539002 (Python Code)

Max Activating Token Index: 63

Text #5

Max Range: 1.4438. Min Range: -1.4438

Max Act: 1.4044. Min Act: -0.0000

Data Index: 1569978 (Python Code)

Max Activating Token Index: 20

Text #6

Max Range: 1.4438. Min Range: -1.4438

Max Act: 1.4005. Min Act: -0.0000

Data Index: 1483101 (Python Code)

Max Activating Token Index: 210

Text #7

Max Range: 1.4438. Min Range: -1.4438

Max Act: 1.3926. Min Act: -0.0000

Data Index: 1527268 (Python Code)

Max Activating Token Index: 224

Text #8

Max Range: 1.4438. Min Range: -1.4438

Max Act: 1.3384. Min Act: -0.0000

Data Index: 1535766 (Python Code)

Max Activating Token Index: 116

Text #9

Max Range: 1.4438. Min Range: -1.4438

Max Act: 1.3637. Min Act: -0.0000

Data Index: 1622057 (Python Code)

Max Activating Token Index: 677

Text #10

Max Range: 1.4438. Min Range: -1.4438

Max Act: 1.3719. Min Act: -0.0000

Data Index: 1459220 (Python Code)

Max Activating Token Index: 633

Text #11

Max Range: 1.4438. Min Range: -1.4438

Max Act: 1.3447. Min Act: -0.0000

Data Index: 1419167 (Python Code)

Max Activating Token Index: 491

Text #12

Max Range: 1.4438. Min Range: -1.4438

Max Act: 1.2402. Min Act: -0.0000

Data Index: 1595308 (Python Code)

Max Activating Token Index: 33

Text #13

Max Range: 1.4438. Min Range: -1.4438

Max Act: 1.2732. Min Act: -0.0000

Data Index: 1592236 (Python Code)

Max Activating Token Index: 445

Text #14

Max Range: 1.4438. Min Range: -1.4438

Max Act: 1.2776. Min Act: -0.0000

Data Index: 1629824 (Python Code)

Max Activating Token Index: 38

Text #15

Max Range: 1.4438. Min Range: -1.4438

Max Act: 1.2814. Min Act: -0.0000

Data Index: 1387862 (Python Code)

Max Activating Token Index: 55

Text #16

Max Range: 1.4438. Min Range: -1.4438

Max Act: 1.2204. Min Act: -0.0000

Data Index: 1449474 (Python Code)

Max Activating Token Index: 740

Text #17

Max Range: 1.4438. Min Range: -1.4438

Max Act: 1.2046. Min Act: -0.0000

Data Index: 1654079 (Python Code)

Max Activating Token Index: 23

Text #18

Max Range: 1.4438. Min Range: -1.4438

Max Act: 1.0683. Min Act: -0.0000

Data Index: 1584333 (Python Code)

Max Activating Token Index: 701

Text #19

Max Range: 1.4438. Min Range: -1.4438

Max Act: 1.1043. Min Act: -0.0000

Data Index: 1369349 (Python Code)

Max Activating Token Index: 80