Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3554 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0744. Min Act: -0.0003

Data Index: 436164 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0737. Min Act: -0.0003

Data Index: 503989 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0752. Min Act: -0.0003

Data Index: 1216952 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0696. Min Act: -0.0003

Data Index: 1082577 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0690. Min Act: -0.0003

Data Index: 259643 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0661. Min Act: -0.0003

Data Index: 506239 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0683. Min Act: -0.0003

Data Index: 549686 (C4 (Web Text))

Max Activating Token Index: 572

Text #7

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0677. Min Act: -0.0003

Data Index: 1117948 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0693. Min Act: -0.0003

Data Index: 1270380 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0667. Min Act: -0.0003

Data Index: 187008 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0665. Min Act: -0.0003

Data Index: 1032177 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0662. Min Act: -0.0003

Data Index: 304321 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0660. Min Act: -0.0003

Data Index: 809462 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0660. Min Act: -0.0003

Data Index: 1349976 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0638. Min Act: -0.0003

Data Index: 210838 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0624. Min Act: -0.0003

Data Index: 850956 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0593. Min Act: -0.0003

Data Index: 113233 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0616. Min Act: -0.0003

Data Index: 567983 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0613. Min Act: -0.0003

Data Index: 1183862 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0561. Min Act: -0.0003

Data Index: 456852 (C4 (Web Text))

Max Activating Token Index: 335