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

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

Neuron 266 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1528. Min Act: -0.0000

Data Index: 1598781 (Python Code)

Max Activating Token Index: 46

Text #1

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1088. Min Act: -0.0000

Data Index: 1467183 (Python Code)

Max Activating Token Index: 323

Text #2

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1049. Min Act: -0.0001

Data Index: 1385748 (Python Code)

Max Activating Token Index: 88

Text #3

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1094. Min Act: -0.0000

Data Index: 1479192 (Python Code)

Max Activating Token Index: 175

Text #4

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0971. Min Act: -0.0001

Data Index: 1368694 (Python Code)

Max Activating Token Index: 185

Text #5

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0987. Min Act: -0.0000

Data Index: 1613115 (Python Code)

Max Activating Token Index: 25

Text #6

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0995. Min Act: -0.0000

Data Index: 1603029 (Python Code)

Max Activating Token Index: 278

Text #7

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0895. Min Act: -0.0000

Data Index: 1481951 (Python Code)

Max Activating Token Index: 515

Text #8

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0751. Min Act: -0.0000

Data Index: 1414179 (Python Code)

Max Activating Token Index: 244

Text #9

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0865. Min Act: -0.0001

Data Index: 1380227 (Python Code)

Max Activating Token Index: 748

Text #10

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0897. Min Act: -0.0000

Data Index: 1448181 (Python Code)

Max Activating Token Index: 675

Text #11

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0966. Min Act: -0.0001

Data Index: 1388118 (Python Code)

Max Activating Token Index: 359

Text #12

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0917. Min Act: -0.0001

Data Index: 1417692 (Python Code)

Max Activating Token Index: 371

Text #13

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0896. Min Act: -0.0000

Data Index: 1389924 (Python Code)

Max Activating Token Index: 56

Text #14

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0887. Min Act: -0.0001

Data Index: 1400085 (Python Code)

Max Activating Token Index: 311

Text #15

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0819. Min Act: -0.0001

Data Index: 1500972 (Python Code)

Max Activating Token Index: 578

Text #16

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0808. Min Act: -0.0001

Data Index: 1433001 (Python Code)

Max Activating Token Index: 638

Text #17

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0907. Min Act: -0.0000

Data Index: 1637442 (Python Code)

Max Activating Token Index: 539

Text #18

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0714. Min Act: -0.0001

Data Index: 1577940 (Python Code)

Max Activating Token Index: 236

Text #19

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0786. Min Act: -0.0000

Data Index: 1494903 (Python Code)

Max Activating Token Index: 572