Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2821 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0624. Min Act: -0.0001

Data Index: 1069866 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0639. Min Act: -0.0001

Data Index: 794575 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0636. Min Act: -0.0001

Data Index: 201348 (C4 (Web Text))

Max Activating Token Index: 734

Text #3

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0571. Min Act: -0.0001

Data Index: 437532 (C4 (Web Text))

Max Activating Token Index: 677

Text #4

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0562. Min Act: -0.0001

Data Index: 277648 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0508. Min Act: -0.0001

Data Index: 322570 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0546. Min Act: -0.0001

Data Index: 831240 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0537. Min Act: -0.0001

Data Index: 853852 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0529. Min Act: -0.0001

Data Index: 926884 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0539. Min Act: -0.0001

Data Index: 531029 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0517. Min Act: -0.0001

Data Index: 1046056 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0518. Min Act: -0.0001

Data Index: 83855 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0540. Min Act: -0.0001

Data Index: 79702 (C4 (Web Text))

Max Activating Token Index: 866

Text #13

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0486. Min Act: -0.0001

Data Index: 338989 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0501. Min Act: -0.0001

Data Index: 414659 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0494. Min Act: -0.0001

Data Index: 289408 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0489. Min Act: -0.0001

Data Index: 332635 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0503. Min Act: -0.0001

Data Index: 625188 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0452. Min Act: -0.0001

Data Index: 810615 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0502. Min Act: -0.0001

Data Index: 1284670 (C4 (Web Text))

Max Activating Token Index: 247