Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 952 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.5054. Min Act: -0.0003

Data Index: 568368 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.4633. Min Act: -0.0003

Data Index: 507488 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.4896. Min Act: -0.0003

Data Index: 33790 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.4584. Min Act: -0.0003

Data Index: 166366 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.4626. Min Act: -0.0003

Data Index: 1277551 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.4726. Min Act: -0.0003

Data Index: 639014 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.4415. Min Act: -0.0003

Data Index: 95483 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.4553. Min Act: -0.0003

Data Index: 173802 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.4544. Min Act: -0.0003

Data Index: 1334798 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.4406. Min Act: -0.0003

Data Index: 15673 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.4431. Min Act: -0.0003

Data Index: 969717 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3803. Min Act: -0.0003

Data Index: 20577 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.4344. Min Act: -0.0003

Data Index: 658723 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3551. Min Act: -0.0003

Data Index: 854785 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.4210. Min Act: -0.0003

Data Index: 1051075 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.4359. Min Act: -0.0003

Data Index: 127595 (C4 (Web Text))

Max Activating Token Index: 879

Text #16

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.4135. Min Act: -0.0003

Data Index: 1249169 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.4235. Min Act: -0.0003

Data Index: 1007763 (C4 (Web Text))

Max Activating Token Index: 719

Text #18

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.3861. Min Act: -0.0003

Data Index: 114918 (C4 (Web Text))

Max Activating Token Index: 627

Text #19

Max Range: 0.5054. Min Range: -0.5054

Max Act: 0.4277. Min Act: -0.0003

Data Index: 140687 (C4 (Web Text))

Max Activating Token Index: 687