Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2247 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0012. Min Act: -0.0002

Data Index: 1417225 (Python Code)

Max Activating Token Index: 1022

Text #1

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0008. Min Act: -0.0002

Data Index: 1479746 (Python Code)

Max Activating Token Index: 397

Text #2

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0007. Min Act: -0.0002

Data Index: 1401662 (Python Code)

Max Activating Token Index: 246

Text #3

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0007. Min Act: -0.0002

Data Index: 1529554 (Python Code)

Max Activating Token Index: 268

Text #4

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0007. Min Act: -0.0002

Data Index: 1551146 (Python Code)

Max Activating Token Index: 195

Text #5

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0007. Min Act: -0.0002

Data Index: 1548893 (Python Code)

Max Activating Token Index: 698

Text #6

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0007. Min Act: -0.0002

Data Index: 1647578 (Python Code)

Max Activating Token Index: 595

Text #7

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0007. Min Act: -0.0002

Data Index: 1427243 (Python Code)

Max Activating Token Index: 338

Text #8

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0007. Min Act: -0.0002

Data Index: 1519957 (Python Code)

Max Activating Token Index: 124

Text #9

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0006. Min Act: -0.0002

Data Index: 1555550 (Python Code)

Max Activating Token Index: 654

Text #10

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0006. Min Act: -0.0002

Data Index: 1468838 (Python Code)

Max Activating Token Index: 1001

Text #11

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0006. Min Act: -0.0002

Data Index: 1619435 (Python Code)

Max Activating Token Index: 717

Text #12

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0006. Min Act: -0.0002

Data Index: 1654353 (Python Code)

Max Activating Token Index: 561

Text #13

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0006. Min Act: -0.0002

Data Index: 1541762 (Python Code)

Max Activating Token Index: 694

Text #14

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0006. Min Act: -0.0002

Data Index: 1391111 (Python Code)

Max Activating Token Index: 185

Text #15

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0006. Min Act: -0.0002

Data Index: 1641268 (Python Code)

Max Activating Token Index: 364

Text #16

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0006. Min Act: -0.0002

Data Index: 1438911 (Python Code)

Max Activating Token Index: 672

Text #17

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0006. Min Act: -0.0002

Data Index: 1571037 (Python Code)

Max Activating Token Index: 541

Text #18

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0006. Min Act: -0.0002

Data Index: 1432264 (Python Code)

Max Activating Token Index: 553

Text #19

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0006. Min Act: -0.0002

Data Index: 1626924 (Python Code)

Max Activating Token Index: 333