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

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

Neuron 2920 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0593. Min Act: -0.0003

Data Index: 784207 (C4 (Web Text))

Max Activating Token Index: 663

Text #1

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0577. Min Act: -0.0003

Data Index: 100266 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0534. Min Act: -0.0003

Data Index: 443561 (C4 (Web Text))

Max Activating Token Index: 587

Text #3

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0550. Min Act: -0.0003

Data Index: 908165 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0530. Min Act: -0.0003

Data Index: 396663 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0541. Min Act: -0.0003

Data Index: 933079 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0471. Min Act: -0.0003

Data Index: 97580 (C4 (Web Text))

Max Activating Token Index: 616

Text #7

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0511. Min Act: -0.0003

Data Index: 799179 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0504. Min Act: -0.0003

Data Index: 809605 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0489. Min Act: -0.0003

Data Index: 382713 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0490. Min Act: -0.0003

Data Index: 275317 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0465. Min Act: -0.0003

Data Index: 546522 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0474. Min Act: -0.0003

Data Index: 1166804 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0473. Min Act: -0.0003

Data Index: 726945 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0481. Min Act: -0.0003

Data Index: 1053666 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0478. Min Act: -0.0003

Data Index: 1039670 (C4 (Web Text))

Max Activating Token Index: 997

Text #16

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0464. Min Act: -0.0003

Data Index: 118694 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0471. Min Act: -0.0003

Data Index: 654714 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0480. Min Act: -0.0003

Data Index: 458603 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0488. Min Act: -0.0003

Data Index: 558806 (C4 (Web Text))

Max Activating Token Index: 335