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

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

Neuron 1063 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0786. Min Act: -0.0002

Data Index: 132509 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0774. Min Act: -0.0002

Data Index: 1139385 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0769. Min Act: -0.0002

Data Index: 1037174 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0722. Min Act: -0.0002

Data Index: 1053741 (C4 (Web Text))

Max Activating Token Index: 553

Text #4

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0731. Min Act: -0.0002

Data Index: 653051 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0747. Min Act: -0.0002

Data Index: 139356 (C4 (Web Text))

Max Activating Token Index: 286

Text #6

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0740. Min Act: -0.0002

Data Index: 493110 (C4 (Web Text))

Max Activating Token Index: 999

Text #7

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0755. Min Act: -0.0002

Data Index: 441330 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0698. Min Act: -0.0002

Data Index: 1167788 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0664. Min Act: -0.0002

Data Index: 286199 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0679. Min Act: -0.0002

Data Index: 748328 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0716. Min Act: -0.0002

Data Index: 890802 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0696. Min Act: -0.0002

Data Index: 230902 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0651. Min Act: -0.0002

Data Index: 1240611 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0707. Min Act: -0.0002

Data Index: 1179226 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0700. Min Act: -0.0002

Data Index: 1021211 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0658. Min Act: -0.0002

Data Index: 717202 (C4 (Web Text))

Max Activating Token Index: 741

Text #17

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0671. Min Act: -0.0002

Data Index: 1332597 (C4 (Web Text))

Max Activating Token Index: 342

Text #18

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0681. Min Act: -0.0002

Data Index: 987265 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0713. Min Act: -0.0002

Data Index: 376305 (C4 (Web Text))

Max Activating Token Index: 729