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

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

Neuron 89 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.1066. Min Act: -0.0001

Data Index: 689347 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.1045. Min Act: -0.0001

Data Index: 456087 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0951. Min Act: -0.0001

Data Index: 855060 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0937. Min Act: -0.0001

Data Index: 179311 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0843. Min Act: -0.0001

Data Index: 13919 (C4 (Web Text))

Max Activating Token Index: 319

Text #5

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0800. Min Act: -0.0001

Data Index: 1267730 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0854. Min Act: -0.0001

Data Index: 763883 (C4 (Web Text))

Max Activating Token Index: 732

Text #7

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0786. Min Act: -0.0001

Data Index: 518434 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0680. Min Act: -0.0001

Data Index: 93878 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0756. Min Act: -0.0001

Data Index: 888606 (C4 (Web Text))

Max Activating Token Index: 630

Text #10

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0746. Min Act: -0.0001

Data Index: 194154 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0682. Min Act: -0.0001

Data Index: 773691 (C4 (Web Text))

Max Activating Token Index: 959

Text #12

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0761. Min Act: -0.0001

Data Index: 1145907 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0689. Min Act: -0.0001

Data Index: 765518 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0694. Min Act: -0.0001

Data Index: 1183463 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0692. Min Act: -0.0001

Data Index: 185636 (C4 (Web Text))

Max Activating Token Index: 363

Text #16

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0663. Min Act: -0.0001

Data Index: 1088785 (C4 (Web Text))

Max Activating Token Index: 524

Text #17

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0722. Min Act: -0.0001

Data Index: 1126792 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0707. Min Act: -0.0001

Data Index: 1353913 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0697. Min Act: -0.0001

Data Index: 494810 (C4 (Web Text))

Max Activating Token Index: 493