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

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

Neuron 310 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: 0.0655. Min Range: -0.0655

Max Act: 0.0655. Min Act: -0.0005

Data Index: 444676 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0605. Min Act: -0.0006

Data Index: 1270810 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0590. Min Act: -0.0006

Data Index: 125931 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0571. Min Act: -0.0006

Data Index: 1292088 (C4 (Web Text))

Max Activating Token Index: 318

Text #4

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0569. Min Act: -0.0006

Data Index: 701097 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0579. Min Act: -0.0005

Data Index: 1305574 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0590. Min Act: -0.0006

Data Index: 719960 (C4 (Web Text))

Max Activating Token Index: 952

Text #7

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0572. Min Act: -0.0006

Data Index: 822139 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0593. Min Act: -0.0006

Data Index: 168090 (C4 (Web Text))

Max Activating Token Index: 939

Text #9

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0579. Min Act: -0.0006

Data Index: 1191353 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0552. Min Act: -0.0006

Data Index: 493901 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0574. Min Act: -0.0006

Data Index: 153563 (C4 (Web Text))

Max Activating Token Index: 772

Text #12

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0566. Min Act: -0.0005

Data Index: 605877 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0561. Min Act: -0.0006

Data Index: 461127 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0517. Min Act: -0.0006

Data Index: 1323455 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0560. Min Act: -0.0005

Data Index: 3411 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0556. Min Act: -0.0006

Data Index: 886259 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0546. Min Act: -0.0006

Data Index: 784560 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0543. Min Act: -0.0006

Data Index: 1141968 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0579. Min Act: -0.0006

Data Index: 1090112 (C4 (Web Text))

Max Activating Token Index: 826