Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1841 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0903. Min Act: -0.0005

Data Index: 1293555 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0828. Min Act: -0.0005

Data Index: 714915 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0830. Min Act: -0.0005

Data Index: 955190 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0818. Min Act: -0.0005

Data Index: 9892 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0776. Min Act: -0.0005

Data Index: 35418 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0823. Min Act: -0.0005

Data Index: 1215823 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0810. Min Act: -0.0005

Data Index: 363692 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0775. Min Act: -0.0005

Data Index: 1141384 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0767. Min Act: -0.0005

Data Index: 1114231 (C4 (Web Text))

Max Activating Token Index: 947

Text #9

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0742. Min Act: -0.0005

Data Index: 1091170 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0741. Min Act: -0.0005

Data Index: 824950 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0753. Min Act: -0.0005

Data Index: 824890 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0718. Min Act: -0.0005

Data Index: 957404 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0750. Min Act: -0.0005

Data Index: 412318 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0699. Min Act: -0.0005

Data Index: 1020931 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0706. Min Act: -0.0005

Data Index: 1157823 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0730. Min Act: -0.0005

Data Index: 1039433 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0713. Min Act: -0.0005

Data Index: 263063 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0703. Min Act: -0.0005

Data Index: 113799 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0711. Min Act: -0.0005

Data Index: 54293 (C4 (Web Text))

Max Activating Token Index: 409