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

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

Neuron 134 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0594. Min Act: -0.0006

Data Index: 1029869 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0582. Min Act: -0.0006

Data Index: 377585 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0567. Min Act: -0.0006

Data Index: 186501 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0563. Min Act: -0.0006

Data Index: 580079 (C4 (Web Text))

Max Activating Token Index: 742

Text #4

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0537. Min Act: -0.0006

Data Index: 376743 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0496. Min Act: -0.0006

Data Index: 461531 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0497. Min Act: -0.0006

Data Index: 1316072 (C4 (Web Text))

Max Activating Token Index: 542

Text #7

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0488. Min Act: -0.0006

Data Index: 563116 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0495. Min Act: -0.0006

Data Index: 1030743 (C4 (Web Text))

Max Activating Token Index: 141

Text #9

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0504. Min Act: -0.0006

Data Index: 395804 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0517. Min Act: -0.0006

Data Index: 1007928 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0495. Min Act: -0.0006

Data Index: 867439 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0466. Min Act: -0.0006

Data Index: 246514 (C4 (Web Text))

Max Activating Token Index: 302

Text #13

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0494. Min Act: -0.0006

Data Index: 449594 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0474. Min Act: -0.0006

Data Index: 72381 (C4 (Web Text))

Max Activating Token Index: 439

Text #15

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0463. Min Act: -0.0006

Data Index: 1066782 (C4 (Web Text))

Max Activating Token Index: 658

Text #16

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0470. Min Act: -0.0006

Data Index: 105781 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0471. Min Act: -0.0006

Data Index: 527743 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0464. Min Act: -0.0006

Data Index: 295866 (C4 (Web Text))

Max Activating Token Index: 442

Text #19

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0463. Min Act: -0.0006

Data Index: 166754 (C4 (Web Text))

Max Activating Token Index: 416