Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2055 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0824. Min Act: -0.0001

Data Index: 958602 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0838. Min Act: -0.0001

Data Index: 1055490 (C4 (Web Text))

Max Activating Token Index: 911

Text #2

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0843. Min Act: -0.0001

Data Index: 531424 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0726. Min Act: -0.0001

Data Index: 964657 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0550. Min Act: -0.0001

Data Index: 114603 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0674. Min Act: -0.0001

Data Index: 287458 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0586. Min Act: -0.0001

Data Index: 874465 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0594. Min Act: -0.0001

Data Index: 865793 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0633. Min Act: -0.0001

Data Index: 820566 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0535. Min Act: -0.0001

Data Index: 400624 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0538. Min Act: -0.0001

Data Index: 51613 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0614. Min Act: -0.0001

Data Index: 1094671 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0668. Min Act: -0.0001

Data Index: 718563 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0532. Min Act: -0.0001

Data Index: 147234 (C4 (Web Text))

Max Activating Token Index: 193

Text #14

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0546. Min Act: -0.0001

Data Index: 1067274 (C4 (Web Text))

Max Activating Token Index: 132

Text #15

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0471. Min Act: -0.0002

Data Index: 542622 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0543. Min Act: -0.0001

Data Index: 1000340 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0545. Min Act: -0.0001

Data Index: 1272168 (C4 (Web Text))

Max Activating Token Index: 849

Text #18

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0521. Min Act: -0.0002

Data Index: 815376 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0530. Min Act: -0.0001

Data Index: 708913 (C4 (Web Text))

Max Activating Token Index: 576