Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1043 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0559. Min Act: -0.0006

Data Index: 51465 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0563. Min Act: -0.0006

Data Index: 657865 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0543. Min Act: -0.0006

Data Index: 100771 (C4 (Web Text))

Max Activating Token Index: 960

Text #3

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0519. Min Act: -0.0006

Data Index: 1021301 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0548. Min Act: -0.0006

Data Index: 702641 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0539. Min Act: -0.0006

Data Index: 369166 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0546. Min Act: -0.0006

Data Index: 1002149 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0537. Min Act: -0.0006

Data Index: 312130 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0514. Min Act: -0.0006

Data Index: 545616 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0510. Min Act: -0.0006

Data Index: 525789 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0504. Min Act: -0.0006

Data Index: 67678 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0513. Min Act: -0.0006

Data Index: 395206 (C4 (Web Text))

Max Activating Token Index: 373

Text #12

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0511. Min Act: -0.0006

Data Index: 298237 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0516. Min Act: -0.0006

Data Index: 669556 (C4 (Web Text))

Max Activating Token Index: 502

Text #14

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0505. Min Act: -0.0006

Data Index: 824818 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0470. Min Act: -0.0006

Data Index: 953963 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0477. Min Act: -0.0006

Data Index: 1211323 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0467. Min Act: -0.0006

Data Index: 248962 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0503. Min Act: -0.0006

Data Index: 891644 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0501. Min Act: -0.0006

Data Index: 388575 (C4 (Web Text))

Max Activating Token Index: 575