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

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

Neuron 1623 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: 0.0665. Min Range: -0.0665

Max Act: 0.0665. Min Act: -0.0003

Data Index: 838561 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0624. Min Act: -0.0003

Data Index: 72601 (C4 (Web Text))

Max Activating Token Index: 600

Text #2

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0602. Min Act: -0.0003

Data Index: 352513 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0579. Min Act: -0.0003

Data Index: 1083847 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0551. Min Act: -0.0003

Data Index: 954189 (C4 (Web Text))

Max Activating Token Index: 971

Text #5

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0559. Min Act: -0.0003

Data Index: 381135 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0541. Min Act: -0.0002

Data Index: 994482 (C4 (Web Text))

Max Activating Token Index: 95

Text #7

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0593. Min Act: -0.0003

Data Index: 1047332 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0533. Min Act: -0.0003

Data Index: 1046061 (C4 (Web Text))

Max Activating Token Index: 193

Text #9

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0537. Min Act: -0.0003

Data Index: 432704 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0527. Min Act: -0.0003

Data Index: 24907 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0541. Min Act: -0.0004

Data Index: 1117004 (C4 (Web Text))

Max Activating Token Index: 385

Text #12

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0534. Min Act: -0.0003

Data Index: 26227 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0536. Min Act: -0.0003

Data Index: 1138817 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0533. Min Act: -0.0004

Data Index: 232824 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0520. Min Act: -0.0003

Data Index: 517247 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0497. Min Act: -0.0003

Data Index: 185447 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0483. Min Act: -0.0003

Data Index: 1356649 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0501. Min Act: -0.0003

Data Index: 1243130 (C4 (Web Text))

Max Activating Token Index: 796

Text #19

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0533. Min Act: -0.0003

Data Index: 500237 (C4 (Web Text))

Max Activating Token Index: 397