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

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

Neuron 3574 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.1133. Min Act: -0.0001

Data Index: 12962 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0769. Min Act: -0.0001

Data Index: 839295 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0794. Min Act: -0.0000

Data Index: 1286302 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0656. Min Act: -0.0001

Data Index: 1468741 (Python Code)

Max Activating Token Index: 859

Text #4

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0696. Min Act: -0.0001

Data Index: 66040 (C4 (Web Text))

Max Activating Token Index: 590

Text #5

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0690. Min Act: -0.0001

Data Index: 894058 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0677. Min Act: -0.0001

Data Index: 460467 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0632. Min Act: -0.0001

Data Index: 1209521 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0660. Min Act: -0.0000

Data Index: 1085949 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0651. Min Act: -0.0001

Data Index: 684377 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0655. Min Act: -0.0001

Data Index: 1054228 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0610. Min Act: -0.0000

Data Index: 917435 (C4 (Web Text))

Max Activating Token Index: 798

Text #12

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0619. Min Act: -0.0001

Data Index: 263829 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0560. Min Act: -0.0001

Data Index: 1098326 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0560. Min Act: -0.0000

Data Index: 1584919 (Python Code)

Max Activating Token Index: 376

Text #15

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0574. Min Act: -0.0001

Data Index: 948231 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0565. Min Act: -0.0001

Data Index: 825835 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0564. Min Act: -0.0000

Data Index: 1526926 (Python Code)

Max Activating Token Index: 820

Text #18

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0545. Min Act: -0.0001

Data Index: 165918 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 0.1133. Min Range: -0.1133

Max Act: 0.0496. Min Act: -0.0001

Data Index: 10724 (C4 (Web Text))

Max Activating Token Index: 393