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

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

Neuron 3525 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0839. Min Range: -1.0839

Max Act: 1.0246. Min Act: -0.0000

Data Index: 420320 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 1.0839. Min Range: -1.0839

Max Act: 1.0570. Min Act: -0.0000

Data Index: 440653 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 1.0839. Min Range: -1.0839

Max Act: 1.0839. Min Act: -0.0000

Data Index: 1056557 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.9429. Min Act: -0.0000

Data Index: 606130 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 1.0839. Min Range: -1.0839

Max Act: 1.0068. Min Act: -0.0000

Data Index: 441926 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 1.0839. Min Range: -1.0839

Max Act: 1.0671. Min Act: -0.0000

Data Index: 5171 (C4 (Web Text))

Max Activating Token Index: 230

Text #6

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.9915. Min Act: -0.0000

Data Index: 455622 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.8424. Min Act: -0.0000

Data Index: 717195 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.8354. Min Act: -0.0000

Data Index: 394987 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.7634. Min Act: -0.0000

Data Index: 241754 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.8036. Min Act: 0.0000

Data Index: 876799 (C4 (Web Text))

Max Activating Token Index: 323

Text #11

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.8075. Min Act: -0.0000

Data Index: 189026 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.8002. Min Act: 0.0000

Data Index: 867172 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.7542. Min Act: 0.0000

Data Index: 1275386 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.7071. Min Act: -0.0000

Data Index: 1325856 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.7243. Min Act: -0.0000

Data Index: 1483349 (Python Code)

Max Activating Token Index: 260

Text #16

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.5809. Min Act: -0.0000

Data Index: 355386 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.6347. Min Act: 0.0000

Data Index: 338562 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.6169. Min Act: -0.0000

Data Index: 726825 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.5657. Min Act: -0.0000

Data Index: 800642 (C4 (Web Text))

Max Activating Token Index: 636