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

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

Neuron 518 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0667. Min Act: -0.0002

Data Index: 1138349 (C4 (Web Text))

Max Activating Token Index: 258

Text #1

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0637. Min Act: -0.0002

Data Index: 1309689 (C4 (Web Text))

Max Activating Token Index: 277

Text #2

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0621. Min Act: -0.0002

Data Index: 498129 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0614. Min Act: -0.0002

Data Index: 65043 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0608. Min Act: -0.0002

Data Index: 693599 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0601. Min Act: -0.0002

Data Index: 186946 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0590. Min Act: -0.0002

Data Index: 374682 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0603. Min Act: -0.0002

Data Index: 386334 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0585. Min Act: -0.0002

Data Index: 257547 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0587. Min Act: -0.0001

Data Index: 767460 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0584. Min Act: -0.0002

Data Index: 891972 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0571. Min Act: -0.0002

Data Index: 343415 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0585. Min Act: -0.0002

Data Index: 1017473 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0576. Min Act: -0.0002

Data Index: 1075465 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0560. Min Act: -0.0002

Data Index: 1106557 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0574. Min Act: -0.0002

Data Index: 786494 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0552. Min Act: -0.0002

Data Index: 21496 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0578. Min Act: -0.0002

Data Index: 1227641 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0566. Min Act: -0.0002

Data Index: 238176 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0562. Min Act: -0.0002

Data Index: 561158 (C4 (Web Text))

Max Activating Token Index: 83