Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1950 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0775. Min Act: -0.0002

Data Index: 843488 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0701. Min Act: -0.0002

Data Index: 118540 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0593. Min Act: -0.0002

Data Index: 1078527 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0563. Min Act: -0.0002

Data Index: 14174 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0579. Min Act: -0.0002

Data Index: 544483 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0574. Min Act: -0.0002

Data Index: 445419 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0553. Min Act: -0.0002

Data Index: 978525 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0517. Min Act: -0.0002

Data Index: 621906 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0519. Min Act: -0.0002

Data Index: 327062 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0546. Min Act: -0.0002

Data Index: 425982 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1042087 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0492. Min Act: -0.0002

Data Index: 327435 (C4 (Web Text))

Max Activating Token Index: 269

Text #12

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0501. Min Act: -0.0002

Data Index: 30416 (C4 (Web Text))

Max Activating Token Index: 624

Text #13

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0484. Min Act: -0.0002

Data Index: 239540 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0487. Min Act: -0.0002

Data Index: 467102 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0497. Min Act: -0.0002

Data Index: 256084 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0518. Min Act: -0.0002

Data Index: 1169060 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0445. Min Act: -0.0002

Data Index: 111332 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0448. Min Act: -0.0002

Data Index: 1265835 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 0.0775. Min Range: -0.0775

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1146470 (C4 (Web Text))

Max Activating Token Index: 509