Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3798 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0570. Min Act: -0.0003

Data Index: 1170687 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0549. Min Act: -0.0004

Data Index: 194974 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0523. Min Act: -0.0003

Data Index: 327988 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0516. Min Act: -0.0003

Data Index: 61276 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0522. Min Act: -0.0003

Data Index: 500447 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0468. Min Act: -0.0003

Data Index: 836723 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0488. Min Act: -0.0003

Data Index: 218495 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0466. Min Act: -0.0003

Data Index: 177374 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0472. Min Act: -0.0003

Data Index: 33287 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0430. Min Act: -0.0003

Data Index: 734979 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0479. Min Act: -0.0003

Data Index: 798579 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0466. Min Act: -0.0003

Data Index: 816673 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0446. Min Act: -0.0003

Data Index: 742298 (C4 (Web Text))

Max Activating Token Index: 689

Text #13

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0442. Min Act: -0.0003

Data Index: 950573 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0458. Min Act: -0.0003

Data Index: 643038 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0453. Min Act: -0.0003

Data Index: 785309 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0459. Min Act: -0.0003

Data Index: 190390 (C4 (Web Text))

Max Activating Token Index: 451

Text #17

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0465. Min Act: -0.0003

Data Index: 1112148 (C4 (Web Text))

Max Activating Token Index: 681

Text #18

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0439. Min Act: -0.0003

Data Index: 257360 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0455. Min Act: -0.0003

Data Index: 265217 (C4 (Web Text))

Max Activating Token Index: 30