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

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

Neuron 3473 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.7988. Min Act: -0.0001

Data Index: 660359 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.7241. Min Act: -0.0001

Data Index: 1243991 (C4 (Web Text))

Max Activating Token Index: 625

Text #2

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.7702. Min Act: -0.0001

Data Index: 820438 (C4 (Web Text))

Max Activating Token Index: 669

Text #3

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6793. Min Act: -0.0002

Data Index: 138148 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6686. Min Act: -0.0001

Data Index: 464636 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6974. Min Act: -0.0002

Data Index: 717905 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6409. Min Act: -0.0001

Data Index: 749645 (C4 (Web Text))

Max Activating Token Index: 656

Text #7

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6431. Min Act: -0.0001

Data Index: 496364 (C4 (Web Text))

Max Activating Token Index: 935

Text #8

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6867. Min Act: -0.0001

Data Index: 489191 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6926. Min Act: -0.0001

Data Index: 577203 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5875. Min Act: -0.0002

Data Index: 319671 (C4 (Web Text))

Max Activating Token Index: 634

Text #11

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6250. Min Act: -0.0002

Data Index: 636945 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6587. Min Act: -0.0001

Data Index: 127591 (C4 (Web Text))

Max Activating Token Index: 3

Text #13

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6663. Min Act: -0.0002

Data Index: 1196079 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6083. Min Act: -0.0001

Data Index: 830025 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6859. Min Act: -0.0002

Data Index: 177532 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6875. Min Act: -0.0001

Data Index: 522768 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6851. Min Act: -0.0001

Data Index: 946648 (C4 (Web Text))

Max Activating Token Index: 758

Text #18

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6377. Min Act: -0.0002

Data Index: 386501 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6341. Min Act: -0.0001

Data Index: 277919 (C4 (Web Text))

Max Activating Token Index: 610