Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4257 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0831. Min Act: -0.0001

Data Index: 1009448 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0702. Min Act: -0.0001

Data Index: 232496 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0665. Min Act: -0.0001

Data Index: 470866 (C4 (Web Text))

Max Activating Token Index: 596

Text #3

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0636. Min Act: -0.0001

Data Index: 833778 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0751. Min Act: -0.0001

Data Index: 874707 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0707. Min Act: -0.0001

Data Index: 618165 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0736. Min Act: -0.0001

Data Index: 411973 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0654. Min Act: -0.0001

Data Index: 1100540 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0662. Min Act: -0.0001

Data Index: 1229619 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0646. Min Act: -0.0001

Data Index: 1160872 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0674. Min Act: -0.0001

Data Index: 312396 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0659. Min Act: -0.0001

Data Index: 432533 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0620. Min Act: -0.0001

Data Index: 1005978 (C4 (Web Text))

Max Activating Token Index: 841

Text #13

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0629. Min Act: -0.0001

Data Index: 30226 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0646. Min Act: -0.0001

Data Index: 1347531 (C4 (Web Text))

Max Activating Token Index: 1015

Text #15

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0625. Min Act: -0.0001

Data Index: 812762 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0605. Min Act: -0.0001

Data Index: 901030 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0577. Min Act: -0.0001

Data Index: 996944 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0561. Min Act: -0.0001

Data Index: 416005 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0569. Min Act: -0.0001

Data Index: 637114 (C4 (Web Text))

Max Activating Token Index: 1018