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

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

Neuron 6117 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4630. Min Range: -1.4630

Max Act: 1.4630. Min Act: -0.0000

Data Index: 1411575 (Python Code)

Max Activating Token Index: 465

Text #1

Max Range: 1.4630. Min Range: -1.4630

Max Act: 1.2089. Min Act: -0.0000

Data Index: 1408554 (Python Code)

Max Activating Token Index: 531

Text #2

Max Range: 1.4630. Min Range: -1.4630

Max Act: 1.2312. Min Act: -0.0000

Data Index: 1489506 (Python Code)

Max Activating Token Index: 313

Text #3

Max Range: 1.4630. Min Range: -1.4630

Max Act: 1.2289. Min Act: -0.0000

Data Index: 1461676 (Python Code)

Max Activating Token Index: 118

Text #4

Max Range: 1.4630. Min Range: -1.4630

Max Act: 1.2218. Min Act: -0.0000

Data Index: 1601902 (Python Code)

Max Activating Token Index: 873

Text #5

Max Range: 1.4630. Min Range: -1.4630

Max Act: 1.3058. Min Act: -0.0000

Data Index: 1412186 (Python Code)

Max Activating Token Index: 725

Text #6

Max Range: 1.4630. Min Range: -1.4630

Max Act: 1.2088. Min Act: -0.0000

Data Index: 1622216 (Python Code)

Max Activating Token Index: 753

Text #7

Max Range: 1.4630. Min Range: -1.4630

Max Act: 1.2011. Min Act: -0.0000

Data Index: 1500732 (Python Code)

Max Activating Token Index: 261

Text #8

Max Range: 1.4630. Min Range: -1.4630

Max Act: 1.1488. Min Act: -0.0000

Data Index: 1638664 (Python Code)

Max Activating Token Index: 640

Text #9

Max Range: 1.4630. Min Range: -1.4630

Max Act: 1.1345. Min Act: -0.0000

Data Index: 1423471 (Python Code)

Max Activating Token Index: 657

Text #10

Max Range: 1.4630. Min Range: -1.4630

Max Act: 1.0978. Min Act: -0.0000

Data Index: 1580649 (Python Code)

Max Activating Token Index: 850

Text #11

Max Range: 1.4630. Min Range: -1.4630

Max Act: 1.0732. Min Act: -0.0000

Data Index: 1601720 (Python Code)

Max Activating Token Index: 250

Text #12

Max Range: 1.4630. Min Range: -1.4630

Max Act: 1.2036. Min Act: -0.0000

Data Index: 1414206 (Python Code)

Max Activating Token Index: 271

Text #13

Max Range: 1.4630. Min Range: -1.4630

Max Act: 1.1099. Min Act: -0.0000

Data Index: 1396987 (Python Code)

Max Activating Token Index: 739

Text #14

Max Range: 1.4630. Min Range: -1.4630

Max Act: 1.1364. Min Act: -0.0000

Data Index: 1473390 (Python Code)

Max Activating Token Index: 383

Text #15

Max Range: 1.4630. Min Range: -1.4630

Max Act: 1.0419. Min Act: -0.0000

Data Index: 1639259 (Python Code)

Max Activating Token Index: 819

Text #16

Max Range: 1.4630. Min Range: -1.4630

Max Act: 1.0984. Min Act: -0.0000

Data Index: 1615828 (Python Code)

Max Activating Token Index: 882

Text #17

Max Range: 1.4630. Min Range: -1.4630

Max Act: 1.0918. Min Act: -0.0000

Data Index: 1621213 (Python Code)

Max Activating Token Index: 915

Text #18

Max Range: 1.4630. Min Range: -1.4630

Max Act: 1.1385. Min Act: -0.0000

Data Index: 1447767 (Python Code)

Max Activating Token Index: 783

Text #19

Max Range: 1.4630. Min Range: -1.4630

Max Act: 1.1092. Min Act: -0.0000

Data Index: 1445650 (Python Code)

Max Activating Token Index: 821