Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1366 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0798. Min Act: -0.0006

Data Index: 956160 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0867. Min Act: -0.0006

Data Index: 72465 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0723. Min Act: -0.0006

Data Index: 510058 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0689. Min Act: -0.0006

Data Index: 33260 (C4 (Web Text))

Max Activating Token Index: 450

Text #4

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0702. Min Act: -0.0006

Data Index: 1270180 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0669. Min Act: -0.0006

Data Index: 1303269 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0693. Min Act: -0.0006

Data Index: 239342 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0675. Min Act: -0.0006

Data Index: 1281602 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0659. Min Act: -0.0006

Data Index: 847798 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0644. Min Act: -0.0006

Data Index: 851298 (C4 (Web Text))

Max Activating Token Index: 619

Text #10

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0675. Min Act: -0.0006

Data Index: 1036063 (C4 (Web Text))

Max Activating Token Index: 954

Text #11

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0660. Min Act: -0.0006

Data Index: 1124610 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0655. Min Act: -0.0006

Data Index: 1227979 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0653. Min Act: -0.0006

Data Index: 414470 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0651. Min Act: -0.0006

Data Index: 903584 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0649. Min Act: -0.0006

Data Index: 1103852 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0648. Min Act: -0.0006

Data Index: 225935 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0637. Min Act: -0.0006

Data Index: 1081688 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0661. Min Act: -0.0006

Data Index: 751383 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0634. Min Act: -0.0006

Data Index: 1157170 (C4 (Web Text))

Max Activating Token Index: 835