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

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

Neuron 821 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0659. Min Act: -0.0003

Data Index: 645914 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0588. Min Act: -0.0003

Data Index: 149105 (C4 (Web Text))

Max Activating Token Index: 676

Text #2

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0576. Min Act: -0.0003

Data Index: 931291 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0594. Min Act: -0.0003

Data Index: 353807 (C4 (Web Text))

Max Activating Token Index: 564

Text #4

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0533. Min Act: -0.0003

Data Index: 1200939 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0537. Min Act: -0.0003

Data Index: 169789 (C4 (Web Text))

Max Activating Token Index: 512

Text #6

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0499. Min Act: -0.0003

Data Index: 299329 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0521. Min Act: -0.0003

Data Index: 1208723 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0513. Min Act: -0.0003

Data Index: 434831 (C4 (Web Text))

Max Activating Token Index: 354

Text #9

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0506. Min Act: -0.0003

Data Index: 179241 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0509. Min Act: -0.0003

Data Index: 1025327 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0486. Min Act: -0.0003

Data Index: 906975 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0489. Min Act: -0.0003

Data Index: 1260577 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0491. Min Act: -0.0003

Data Index: 500932 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0479. Min Act: -0.0004

Data Index: 1314904 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0488. Min Act: -0.0003

Data Index: 851877 (C4 (Web Text))

Max Activating Token Index: 479

Text #16

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0467. Min Act: -0.0003

Data Index: 958422 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0497. Min Act: -0.0003

Data Index: 712365 (C4 (Web Text))

Max Activating Token Index: 667

Text #18

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0473. Min Act: -0.0003

Data Index: 1172136 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0481. Min Act: -0.0003

Data Index: 1293140 (C4 (Web Text))

Max Activating Token Index: 716