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

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

Neuron 2210 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: 0.1054. Min Range: -0.1054

Max Act: 0.1054. Min Act: -0.0001

Data Index: 177792 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.1007. Min Act: -0.0001

Data Index: 643921 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0939. Min Act: -0.0001

Data Index: 1124606 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0800. Min Act: -0.0001

Data Index: 1105681 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0828. Min Act: -0.0001

Data Index: 857773 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0769. Min Act: -0.0001

Data Index: 152261 (C4 (Web Text))

Max Activating Token Index: 817

Text #6

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0764. Min Act: -0.0001

Data Index: 1201353 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0741. Min Act: -0.0001

Data Index: 1301259 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0762. Min Act: -0.0001

Data Index: 1118450 (C4 (Web Text))

Max Activating Token Index: 754

Text #9

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0732. Min Act: -0.0001

Data Index: 554967 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0777. Min Act: -0.0001

Data Index: 1145344 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0774. Min Act: -0.0001

Data Index: 363665 (C4 (Web Text))

Max Activating Token Index: 890

Text #12

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0696. Min Act: -0.0001

Data Index: 1031501 (C4 (Web Text))

Max Activating Token Index: 688

Text #13

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0743. Min Act: -0.0001

Data Index: 378236 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0713. Min Act: -0.0001

Data Index: 356148 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0711. Min Act: -0.0001

Data Index: 211380 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0703. Min Act: -0.0001

Data Index: 871494 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0705. Min Act: -0.0001

Data Index: 552365 (C4 (Web Text))

Max Activating Token Index: 597

Text #18

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0674. Min Act: -0.0001

Data Index: 912460 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0739. Min Act: -0.0001

Data Index: 639525 (C4 (Web Text))

Max Activating Token Index: 892