Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 78 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0678. Min Act: -0.0004

Data Index: 593502 (C4 (Web Text))

Max Activating Token Index: 789

Text #1

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0649. Min Act: -0.0003

Data Index: 723724 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0628. Min Act: -0.0003

Data Index: 703652 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0593. Min Act: -0.0003

Data Index: 663982 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0636. Min Act: -0.0003

Data Index: 669901 (C4 (Web Text))

Max Activating Token Index: 792

Text #5

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0612. Min Act: -0.0003

Data Index: 370958 (C4 (Web Text))

Max Activating Token Index: 834

Text #6

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0606. Min Act: -0.0003

Data Index: 940187 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0599. Min Act: -0.0003

Data Index: 501942 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0615. Min Act: -0.0003

Data Index: 1291528 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0566. Min Act: -0.0003

Data Index: 479452 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0585. Min Act: -0.0003

Data Index: 991743 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0572. Min Act: -0.0003

Data Index: 712738 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0605. Min Act: -0.0003

Data Index: 269664 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0582. Min Act: -0.0003

Data Index: 447491 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0578. Min Act: -0.0003

Data Index: 63082 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0566. Min Act: -0.0003

Data Index: 795485 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0555. Min Act: -0.0003

Data Index: 620607 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0568. Min Act: -0.0004

Data Index: 732306 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0545. Min Act: -0.0003

Data Index: 1068446 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 0.0678. Min Range: -0.0678

Max Act: 0.0543. Min Act: -0.0003

Data Index: 194569 (C4 (Web Text))

Max Activating Token Index: 1000