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

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

Neuron 2480 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0777. Min Act: -0.0002

Data Index: 1227171 (C4 (Web Text))

Max Activating Token Index: 580

Text #1

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0798. Min Act: -0.0003

Data Index: 879731 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0733. Min Act: -0.0003

Data Index: 1235715 (C4 (Web Text))

Max Activating Token Index: 293

Text #3

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0754. Min Act: -0.0003

Data Index: 1356903 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0678. Min Act: -0.0003

Data Index: 994737 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0692. Min Act: -0.0003

Data Index: 684958 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0690. Min Act: -0.0003

Data Index: 943237 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0691. Min Act: -0.0003

Data Index: 417029 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0700. Min Act: -0.0003

Data Index: 992415 (C4 (Web Text))

Max Activating Token Index: 461

Text #9

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0650. Min Act: -0.0003

Data Index: 264855 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0677. Min Act: -0.0003

Data Index: 902690 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0662. Min Act: -0.0003

Data Index: 79656 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0676. Min Act: -0.0003

Data Index: 140327 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0661. Min Act: -0.0002

Data Index: 803399 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0658. Min Act: -0.0003

Data Index: 262651 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0660. Min Act: -0.0003

Data Index: 195186 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0631. Min Act: -0.0003

Data Index: 209907 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0639. Min Act: -0.0003

Data Index: 456074 (C4 (Web Text))

Max Activating Token Index: 663

Text #18

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0642. Min Act: -0.0003

Data Index: 882361 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0677. Min Act: -0.0003

Data Index: 212480 (C4 (Web Text))

Max Activating Token Index: 700