Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1647 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0801. Min Act: -0.0006

Data Index: 68991 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0845. Min Act: -0.0006

Data Index: 32907 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0774. Min Act: -0.0006

Data Index: 568545 (C4 (Web Text))

Max Activating Token Index: 930

Text #3

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0737. Min Act: -0.0006

Data Index: 1035924 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0699. Min Act: -0.0006

Data Index: 999656 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0693. Min Act: -0.0006

Data Index: 284422 (C4 (Web Text))

Max Activating Token Index: 394

Text #6

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0706. Min Act: -0.0006

Data Index: 1331199 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0697. Min Act: -0.0006

Data Index: 1007892 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0700. Min Act: -0.0006

Data Index: 581086 (C4 (Web Text))

Max Activating Token Index: 384

Text #9

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0684. Min Act: -0.0006

Data Index: 199955 (C4 (Web Text))

Max Activating Token Index: 799

Text #10

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0699. Min Act: -0.0006

Data Index: 1303869 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0668. Min Act: -0.0006

Data Index: 1287300 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0661. Min Act: -0.0006

Data Index: 666876 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0658. Min Act: -0.0006

Data Index: 933392 (C4 (Web Text))

Max Activating Token Index: 871

Text #14

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0669. Min Act: -0.0006

Data Index: 698933 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0680. Min Act: -0.0006

Data Index: 1259020 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0669. Min Act: -0.0006

Data Index: 636279 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0651. Min Act: -0.0006

Data Index: 1051625 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0664. Min Act: -0.0006

Data Index: 804334 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0664. Min Act: -0.0006

Data Index: 1160217 (C4 (Web Text))

Max Activating Token Index: 12