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

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

Neuron 1817 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: 0.0631. Min Range: -0.0631

Max Act: 0.0631. Min Act: -0.0006

Data Index: 519135 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0571. Min Act: -0.0006

Data Index: 561754 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0568. Min Act: -0.0006

Data Index: 1213824 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0569. Min Act: -0.0006

Data Index: 452398 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0556. Min Act: -0.0006

Data Index: 1112015 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0550. Min Act: -0.0006

Data Index: 1092131 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0526. Min Act: -0.0006

Data Index: 138726 (C4 (Web Text))

Max Activating Token Index: 872

Text #7

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0526. Min Act: -0.0006

Data Index: 830175 (C4 (Web Text))

Max Activating Token Index: 906

Text #8

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0527. Min Act: -0.0006

Data Index: 729232 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0518. Min Act: -0.0006

Data Index: 1268768 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0540. Min Act: -0.0006

Data Index: 1137132 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0497. Min Act: -0.0006

Data Index: 342452 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0515. Min Act: -0.0006

Data Index: 1136906 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0505. Min Act: -0.0006

Data Index: 447173 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0480. Min Act: -0.0006

Data Index: 877460 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0502. Min Act: -0.0006

Data Index: 1147656 (C4 (Web Text))

Max Activating Token Index: 634

Text #16

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0497. Min Act: -0.0006

Data Index: 454075 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0518. Min Act: -0.0006

Data Index: 188546 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0473. Min Act: -0.0006

Data Index: 787458 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0486. Min Act: -0.0006

Data Index: 537020 (C4 (Web Text))

Max Activating Token Index: 839