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

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

Neuron 282 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: 0.0667. Min Range: -0.0667

Max Act: 0.0666. Min Act: -0.0006

Data Index: 362028 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0653. Min Act: -0.0006

Data Index: 848572 (C4 (Web Text))

Max Activating Token Index: 385

Text #2

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0667. Min Act: -0.0006

Data Index: 128305 (C4 (Web Text))

Max Activating Token Index: 760

Text #3

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0620. Min Act: -0.0006

Data Index: 838444 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0620. Min Act: -0.0006

Data Index: 886613 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0621. Min Act: -0.0006

Data Index: 295688 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0596. Min Act: -0.0006

Data Index: 1112057 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0629. Min Act: -0.0006

Data Index: 221545 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0592. Min Act: -0.0006

Data Index: 499687 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0627. Min Act: -0.0006

Data Index: 504354 (C4 (Web Text))

Max Activating Token Index: 912

Text #10

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0586. Min Act: -0.0006

Data Index: 407612 (C4 (Web Text))

Max Activating Token Index: 894

Text #11

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0581. Min Act: -0.0006

Data Index: 319054 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0598. Min Act: -0.0006

Data Index: 1224975 (C4 (Web Text))

Max Activating Token Index: 138

Text #13

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0570. Min Act: -0.0006

Data Index: 364292 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0557. Min Act: -0.0006

Data Index: 742616 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0570. Min Act: -0.0006

Data Index: 214801 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0557. Min Act: -0.0006

Data Index: 337450 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0530. Min Act: -0.0006

Data Index: 143196 (C4 (Web Text))

Max Activating Token Index: 991

Text #18

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0560. Min Act: -0.0006

Data Index: 768114 (C4 (Web Text))

Max Activating Token Index: 919

Text #19

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0571. Min Act: -0.0006

Data Index: 204511 (C4 (Web Text))

Max Activating Token Index: 959