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

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

Neuron 5667 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4887. Min Range: -0.4887

Max Act: 0.4887. Min Act: -0.0000

Data Index: 1388290 (Python Code)

Max Activating Token Index: 65

Text #1

Max Range: 0.4887. Min Range: -0.4887

Max Act: 0.4594. Min Act: -0.0000

Data Index: 1534862 (Python Code)

Max Activating Token Index: 19

Text #2

Max Range: 0.4887. Min Range: -0.4887

Max Act: 0.4086. Min Act: -0.0000

Data Index: 1487833 (Python Code)

Max Activating Token Index: 133

Text #3

Max Range: 0.4887. Min Range: -0.4887

Max Act: 0.3916. Min Act: -0.0000

Data Index: 1507294 (Python Code)

Max Activating Token Index: 183

Text #4

Max Range: 0.4887. Min Range: -0.4887

Max Act: 0.3745. Min Act: -0.0000

Data Index: 1460999 (Python Code)

Max Activating Token Index: 57

Text #5

Max Range: 0.4887. Min Range: -0.4887

Max Act: 0.3598. Min Act: -0.0000

Data Index: 1481687 (Python Code)

Max Activating Token Index: 90

Text #6

Max Range: 0.4887. Min Range: -0.4887

Max Act: 0.3345. Min Act: -0.0000

Data Index: 785011 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 0.4887. Min Range: -0.4887

Max Act: 0.3523. Min Act: -0.0000

Data Index: 637511 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 0.4887. Min Range: -0.4887

Max Act: 0.3222. Min Act: -0.0000

Data Index: 1469338 (Python Code)

Max Activating Token Index: 55

Text #9

Max Range: 0.4887. Min Range: -0.4887

Max Act: 0.3196. Min Act: -0.0000

Data Index: 1254137 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 0.4887. Min Range: -0.4887

Max Act: 0.2889. Min Act: -0.0000

Data Index: 790961 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 0.4887. Min Range: -0.4887

Max Act: 0.3038. Min Act: -0.0000

Data Index: 1526401 (Python Code)

Max Activating Token Index: 53

Text #12

Max Range: 0.4887. Min Range: -0.4887

Max Act: 0.3027. Min Act: -0.0000

Data Index: 592211 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 0.4887. Min Range: -0.4887

Max Act: 0.2914. Min Act: -0.0000

Data Index: 1512004 (Python Code)

Max Activating Token Index: 19

Text #14

Max Range: 0.4887. Min Range: -0.4887

Max Act: 0.2785. Min Act: -0.0000

Data Index: 214515 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 0.4887. Min Range: -0.4887

Max Act: 0.2949. Min Act: -0.0000

Data Index: 1544358 (Python Code)

Max Activating Token Index: 45

Text #16

Max Range: 0.4887. Min Range: -0.4887

Max Act: 0.2976. Min Act: -0.0000

Data Index: 1306505 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 0.4887. Min Range: -0.4887

Max Act: 0.3011. Min Act: -0.0000

Data Index: 1424797 (Python Code)

Max Activating Token Index: 120

Text #18

Max Range: 0.4887. Min Range: -0.4887

Max Act: 0.2900. Min Act: -0.0000

Data Index: 1544903 (Python Code)

Max Activating Token Index: 140

Text #19

Max Range: 0.4887. Min Range: -0.4887

Max Act: 0.2776. Min Act: -0.0000

Data Index: 646132 (C4 (Web Text))

Max Activating Token Index: 369