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

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

Neuron 3418 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6849. Min Range: -2.6849

Max Act: 2.6849. Min Act: -0.0000

Data Index: 1403788 (Python Code)

Max Activating Token Index: 144

Text #1

Max Range: 2.6849. Min Range: -2.6849

Max Act: 2.3214. Min Act: -0.0000

Data Index: 1430871 (Python Code)

Max Activating Token Index: 600

Text #2

Max Range: 2.6849. Min Range: -2.6849

Max Act: 2.2913. Min Act: -0.0000

Data Index: 1505791 (Python Code)

Max Activating Token Index: 809

Text #3

Max Range: 2.6849. Min Range: -2.6849

Max Act: 2.0179. Min Act: -0.0000

Data Index: 1593425 (Python Code)

Max Activating Token Index: 362

Text #4

Max Range: 2.6849. Min Range: -2.6849

Max Act: 2.0985. Min Act: -0.0000

Data Index: 1478811 (Python Code)

Max Activating Token Index: 466

Text #5

Max Range: 2.6849. Min Range: -2.6849

Max Act: 2.0571. Min Act: -0.0000

Data Index: 1652396 (Python Code)

Max Activating Token Index: 891

Text #6

Max Range: 2.6849. Min Range: -2.6849

Max Act: 2.0793. Min Act: -0.0000

Data Index: 1385324 (Python Code)

Max Activating Token Index: 127

Text #7

Max Range: 2.6849. Min Range: -2.6849

Max Act: 2.0019. Min Act: -0.0000

Data Index: 1650298 (Python Code)

Max Activating Token Index: 398

Text #8

Max Range: 2.6849. Min Range: -2.6849

Max Act: 1.9328. Min Act: -0.0000

Data Index: 1374873 (Python Code)

Max Activating Token Index: 990

Text #9

Max Range: 2.6849. Min Range: -2.6849

Max Act: 1.9765. Min Act: -0.0000

Data Index: 1369857 (Python Code)

Max Activating Token Index: 589

Text #10

Max Range: 2.6849. Min Range: -2.6849

Max Act: 1.9317. Min Act: -0.0000

Data Index: 1363957 (Python Code)

Max Activating Token Index: 557

Text #11

Max Range: 2.6849. Min Range: -2.6849

Max Act: 1.9618. Min Act: -0.0000

Data Index: 1547991 (Python Code)

Max Activating Token Index: 175

Text #12

Max Range: 2.6849. Min Range: -2.6849

Max Act: 1.7431. Min Act: -0.0000

Data Index: 1631937 (Python Code)

Max Activating Token Index: 209

Text #13

Max Range: 2.6849. Min Range: -2.6849

Max Act: 1.7972. Min Act: -0.0000

Data Index: 1426416 (Python Code)

Max Activating Token Index: 887

Text #14

Max Range: 2.6849. Min Range: -2.6849

Max Act: 1.7752. Min Act: -0.0000

Data Index: 1591479 (Python Code)

Max Activating Token Index: 420

Text #15

Max Range: 2.6849. Min Range: -2.6849

Max Act: 1.7138. Min Act: -0.0000

Data Index: 1629774 (Python Code)

Max Activating Token Index: 273

Text #16

Max Range: 2.6849. Min Range: -2.6849

Max Act: 1.8199. Min Act: -0.0000

Data Index: 1468045 (Python Code)

Max Activating Token Index: 899

Text #17

Max Range: 2.6849. Min Range: -2.6849

Max Act: 1.8047. Min Act: -0.0000

Data Index: 1488951 (Python Code)

Max Activating Token Index: 100

Text #18

Max Range: 2.6849. Min Range: -2.6849

Max Act: 1.8334. Min Act: -0.0000

Data Index: 1656041 (Python Code)

Max Activating Token Index: 908

Text #19

Max Range: 2.6849. Min Range: -2.6849

Max Act: 1.7827. Min Act: -0.0000

Data Index: 1604322 (Python Code)

Max Activating Token Index: 639