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

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

Neuron 256 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0521. Min Act: -0.0004

Data Index: 809734 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0615. Min Act: -0.0004

Data Index: 597630 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0476. Min Act: -0.0004

Data Index: 322175 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0584. Min Act: -0.0004

Data Index: 1011748 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0555. Min Act: -0.0004

Data Index: 954811 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0432. Min Act: -0.0004

Data Index: 916920 (C4 (Web Text))

Max Activating Token Index: 577

Text #6

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0499. Min Act: -0.0004

Data Index: 752465 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0534. Min Act: -0.0004

Data Index: 1303606 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0562. Min Act: -0.0004

Data Index: 1025763 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0530. Min Act: -0.0004

Data Index: 1182278 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0546. Min Act: -0.0004

Data Index: 1032321 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0522. Min Act: -0.0004

Data Index: 162931 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0464. Min Act: -0.0004

Data Index: 585984 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0479. Min Act: -0.0004

Data Index: 1044535 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0439. Min Act: -0.0004

Data Index: 918256 (C4 (Web Text))

Max Activating Token Index: 330

Text #15

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0514. Min Act: -0.0004

Data Index: 601200 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0495. Min Act: -0.0004

Data Index: 461428 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0435. Min Act: -0.0004

Data Index: 625601 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0398. Min Act: -0.0004

Data Index: 746364 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0496. Min Act: -0.0004

Data Index: 1264345 (C4 (Web Text))

Max Activating Token Index: 434