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

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

Neuron 4296 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3374. Min Range: -2.3374

Max Act: 2.3374. Min Act: -0.0000

Data Index: 1552159 (Python Code)

Max Activating Token Index: 80

Text #1

Max Range: 2.3374. Min Range: -2.3374

Max Act: 2.1953. Min Act: -0.0000

Data Index: 1571016 (Python Code)

Max Activating Token Index: 159

Text #2

Max Range: 2.3374. Min Range: -2.3374

Max Act: 1.6140. Min Act: -0.0000

Data Index: 1528098 (Python Code)

Max Activating Token Index: 943

Text #3

Max Range: 2.3374. Min Range: -2.3374

Max Act: 1.7478. Min Act: -0.0000

Data Index: 1440848 (Python Code)

Max Activating Token Index: 969

Text #4

Max Range: 2.3374. Min Range: -2.3374

Max Act: 1.7238. Min Act: -0.0000

Data Index: 1374587 (Python Code)

Max Activating Token Index: 620

Text #5

Max Range: 2.3374. Min Range: -2.3374

Max Act: 1.5757. Min Act: -0.0000

Data Index: 1510511 (Python Code)

Max Activating Token Index: 310

Text #6

Max Range: 2.3374. Min Range: -2.3374

Max Act: 1.5121. Min Act: -0.0000

Data Index: 1410262 (Python Code)

Max Activating Token Index: 103

Text #7

Max Range: 2.3374. Min Range: -2.3374

Max Act: 1.3522. Min Act: -0.0000

Data Index: 1388242 (Python Code)

Max Activating Token Index: 552

Text #8

Max Range: 2.3374. Min Range: -2.3374

Max Act: 1.4332. Min Act: -0.0000

Data Index: 1365685 (Python Code)

Max Activating Token Index: 10

Text #9

Max Range: 2.3374. Min Range: -2.3374

Max Act: 1.3787. Min Act: -0.0000

Data Index: 1512611 (Python Code)

Max Activating Token Index: 832

Text #10

Max Range: 2.3374. Min Range: -2.3374

Max Act: 1.3302. Min Act: -0.0000

Data Index: 1415365 (Python Code)

Max Activating Token Index: 21

Text #11

Max Range: 2.3374. Min Range: -2.3374

Max Act: 1.2785. Min Act: -0.0000

Data Index: 1556911 (Python Code)

Max Activating Token Index: 103

Text #12

Max Range: 2.3374. Min Range: -2.3374

Max Act: 1.2295. Min Act: -0.0000

Data Index: 1468892 (Python Code)

Max Activating Token Index: 783

Text #13

Max Range: 2.3374. Min Range: -2.3374

Max Act: 1.1744. Min Act: -0.0000

Data Index: 1629561 (Python Code)

Max Activating Token Index: 269

Text #14

Max Range: 2.3374. Min Range: -2.3374

Max Act: 1.2105. Min Act: -0.0000

Data Index: 1431683 (Python Code)

Max Activating Token Index: 85

Text #15

Max Range: 2.3374. Min Range: -2.3374

Max Act: 1.1432. Min Act: -0.0000

Data Index: 1644568 (Python Code)

Max Activating Token Index: 257

Text #16

Max Range: 2.3374. Min Range: -2.3374

Max Act: 1.1842. Min Act: -0.0000

Data Index: 1622117 (Python Code)

Max Activating Token Index: 62

Text #17

Max Range: 2.3374. Min Range: -2.3374

Max Act: 1.1425. Min Act: -0.0000

Data Index: 1369646 (Python Code)

Max Activating Token Index: 169

Text #18

Max Range: 2.3374. Min Range: -2.3374

Max Act: 1.1006. Min Act: -0.0000

Data Index: 1521542 (Python Code)

Max Activating Token Index: 882

Text #19

Max Range: 2.3374. Min Range: -2.3374

Max Act: 1.0930. Min Act: -0.0000

Data Index: 1544163 (Python Code)

Max Activating Token Index: 118