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

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

Neuron 819 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.4683. Min Act: -0.0001

Data Index: 1346114 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.4330. Min Act: -0.0001

Data Index: 1144247 (C4 (Web Text))

Max Activating Token Index: 904

Text #2

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.4123. Min Act: -0.0001

Data Index: 814052 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.4228. Min Act: -0.0001

Data Index: 546746 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3882. Min Act: -0.0001

Data Index: 964327 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3702. Min Act: -0.0001

Data Index: 1194089 (C4 (Web Text))

Max Activating Token Index: 568

Text #6

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.4087. Min Act: -0.0001

Data Index: 96539 (C4 (Web Text))

Max Activating Token Index: 699

Text #7

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3933. Min Act: -0.0001

Data Index: 1068353 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.4010. Min Act: -0.0001

Data Index: 672526 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3887. Min Act: -0.0001

Data Index: 426814 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3998. Min Act: -0.0001

Data Index: 1325297 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3787. Min Act: -0.0001

Data Index: 1021300 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3774. Min Act: -0.0001

Data Index: 799789 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.4155. Min Act: -0.0001

Data Index: 160489 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3829. Min Act: -0.0001

Data Index: 272312 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3812. Min Act: -0.0001

Data Index: 1081310 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3674. Min Act: -0.0001

Data Index: 954414 (C4 (Web Text))

Max Activating Token Index: 968

Text #17

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3785. Min Act: -0.0001

Data Index: 1886 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3734. Min Act: -0.0001

Data Index: 570436 (C4 (Web Text))

Max Activating Token Index: 910

Text #19

Max Range: 0.4683. Min Range: -0.4683

Max Act: 0.3726. Min Act: -0.0001

Data Index: 1212952 (C4 (Web Text))

Max Activating Token Index: 800