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

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

Neuron 347 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0661. Min Act: -0.0006

Data Index: 27507 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0631. Min Act: -0.0006

Data Index: 1409731 (Python Code)

Max Activating Token Index: 489

Text #2

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0725. Min Act: -0.0006

Data Index: 23171 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0689. Min Act: -0.0006

Data Index: 177663 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0737. Min Act: -0.0006

Data Index: 249291 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0722. Min Act: -0.0006

Data Index: 349854 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0715. Min Act: -0.0006

Data Index: 1240237 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0672. Min Act: -0.0006

Data Index: 680818 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0695. Min Act: -0.0006

Data Index: 1015952 (C4 (Web Text))

Max Activating Token Index: 1019

Text #9

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0629. Min Act: -0.0006

Data Index: 612397 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0691. Min Act: -0.0006

Data Index: 1101238 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0846. Min Act: -0.0006

Data Index: 648662 (C4 (Web Text))

Max Activating Token Index: 773

Text #12

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0638. Min Act: -0.0006

Data Index: 184883 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0638. Min Act: -0.0006

Data Index: 632627 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0629. Min Act: -0.0006

Data Index: 35590 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0641. Min Act: -0.0006

Data Index: 1064914 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0646. Min Act: -0.0006

Data Index: 714467 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0683. Min Act: -0.0006

Data Index: 895661 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0724. Min Act: -0.0006

Data Index: 626429 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0649. Min Act: -0.0006

Data Index: 54824 (C4 (Web Text))

Max Activating Token Index: 699