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

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

Neuron 1757 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: 0.0535. Min Range: -0.0535

Max Act: 0.0535. Min Act: -0.0004

Data Index: 947884 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0535. Min Act: -0.0004

Data Index: 68053 (C4 (Web Text))

Max Activating Token Index: 445

Text #2

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0485. Min Act: -0.0004

Data Index: 689517 (C4 (Web Text))

Max Activating Token Index: 656

Text #3

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0532. Min Act: -0.0004

Data Index: 24358 (C4 (Web Text))

Max Activating Token Index: 949

Text #4

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0504. Min Act: -0.0004

Data Index: 985529 (C4 (Web Text))

Max Activating Token Index: 181

Text #5

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0502. Min Act: -0.0004

Data Index: 693535 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0523. Min Act: -0.0004

Data Index: 20361 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0489. Min Act: -0.0004

Data Index: 212792 (C4 (Web Text))

Max Activating Token Index: 356

Text #8

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0481. Min Act: -0.0004

Data Index: 299739 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0469. Min Act: -0.0004

Data Index: 1059711 (C4 (Web Text))

Max Activating Token Index: 621

Text #10

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0498. Min Act: -0.0004

Data Index: 975483 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0511. Min Act: -0.0004

Data Index: 327964 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0483. Min Act: -0.0004

Data Index: 628848 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0465. Min Act: -0.0004

Data Index: 1020578 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0512. Min Act: -0.0004

Data Index: 886814 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0495. Min Act: -0.0004

Data Index: 181515 (C4 (Web Text))

Max Activating Token Index: 474

Text #16

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0488. Min Act: -0.0004

Data Index: 856500 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0504. Min Act: -0.0004

Data Index: 872527 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0472. Min Act: -0.0004

Data Index: 811235 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0415. Min Act: -0.0004

Data Index: 863330 (C4 (Web Text))

Max Activating Token Index: 581