Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4128 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0737. Min Range: -1.0737

Max Act: 1.0518. Min Act: -0.0000

Data Index: 1642351 (Python Code)

Max Activating Token Index: 761

Text #1

Max Range: 1.0737. Min Range: -1.0737

Max Act: 1.0737. Min Act: -0.0000

Data Index: 1645939 (Python Code)

Max Activating Token Index: 34

Text #2

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.9571. Min Act: -0.0000

Data Index: 1463816 (Python Code)

Max Activating Token Index: 167

Text #3

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.8607. Min Act: -0.0000

Data Index: 1575243 (Python Code)

Max Activating Token Index: 172

Text #4

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.9356. Min Act: -0.0000

Data Index: 1608985 (Python Code)

Max Activating Token Index: 109

Text #5

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.8121. Min Act: -0.0000

Data Index: 1557474 (Python Code)

Max Activating Token Index: 67

Text #6

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.8401. Min Act: -0.0000

Data Index: 1533505 (Python Code)

Max Activating Token Index: 87

Text #7

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.7595. Min Act: -0.0000

Data Index: 1384104 (Python Code)

Max Activating Token Index: 24

Text #8

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.7673. Min Act: -0.0000

Data Index: 1541319 (Python Code)

Max Activating Token Index: 213

Text #9

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.8089. Min Act: -0.0000

Data Index: 1622149 (Python Code)

Max Activating Token Index: 102

Text #10

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.7212. Min Act: -0.0000

Data Index: 1536242 (Python Code)

Max Activating Token Index: 277

Text #11

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.8144. Min Act: -0.0000

Data Index: 1385881 (Python Code)

Max Activating Token Index: 233

Text #12

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.6889. Min Act: -0.0000

Data Index: 1646984 (Python Code)

Max Activating Token Index: 82

Text #13

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.7062. Min Act: -0.0000

Data Index: 1485827 (Python Code)

Max Activating Token Index: 202

Text #14

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.7698. Min Act: -0.0000

Data Index: 1653864 (Python Code)

Max Activating Token Index: 170

Text #15

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.6573. Min Act: -0.0000

Data Index: 1539591 (Python Code)

Max Activating Token Index: 595

Text #16

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.6084. Min Act: -0.0000

Data Index: 1626106 (Python Code)

Max Activating Token Index: 203

Text #17

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.6418. Min Act: -0.0000

Data Index: 1574329 (Python Code)

Max Activating Token Index: 534

Text #18

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.8033. Min Act: -0.0000

Data Index: 1458071 (Python Code)

Max Activating Token Index: 199

Text #19

Max Range: 1.0737. Min Range: -1.0737

Max Act: 0.6453. Min Act: -0.0000

Data Index: 1640742 (Python Code)

Max Activating Token Index: 124