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

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

Neuron 446 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: 0.0574. Min Range: -0.0574

Max Act: 0.0574. Min Act: -0.0006

Data Index: 610859 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0523. Min Act: -0.0006

Data Index: 668805 (C4 (Web Text))

Max Activating Token Index: 692

Text #2

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0475. Min Act: -0.0006

Data Index: 1201147 (C4 (Web Text))

Max Activating Token Index: 653

Text #3

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0428. Min Act: -0.0006

Data Index: 800415 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0412. Min Act: -0.0005

Data Index: 350592 (C4 (Web Text))

Max Activating Token Index: 793

Text #5

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0418. Min Act: -0.0006

Data Index: 22503 (C4 (Web Text))

Max Activating Token Index: 509

Text #6

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0401. Min Act: -0.0006

Data Index: 1302680 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0395. Min Act: -0.0006

Data Index: 378954 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0404. Min Act: -0.0006

Data Index: 1285005 (C4 (Web Text))

Max Activating Token Index: 589

Text #9

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0413. Min Act: -0.0006

Data Index: 175075 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0407. Min Act: -0.0006

Data Index: 816466 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0382. Min Act: -0.0006

Data Index: 1337264 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0387. Min Act: -0.0006

Data Index: 1294133 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0394. Min Act: -0.0006

Data Index: 968280 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0392. Min Act: -0.0006

Data Index: 175184 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0396. Min Act: -0.0006

Data Index: 1079646 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0389. Min Act: -0.0006

Data Index: 885604 (C4 (Web Text))

Max Activating Token Index: 462

Text #17

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0388. Min Act: -0.0006

Data Index: 1031843 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0386. Min Act: -0.0006

Data Index: 758093 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0384. Min Act: -0.0006

Data Index: 196427 (C4 (Web Text))

Max Activating Token Index: 775