Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 733 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0834. Min Act: -0.0003

Data Index: 365183 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0716. Min Act: -0.0003

Data Index: 1038197 (C4 (Web Text))

Max Activating Token Index: 626

Text #2

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0667. Min Act: -0.0003

Data Index: 684248 (C4 (Web Text))

Max Activating Token Index: 943

Text #3

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0683. Min Act: -0.0003

Data Index: 1617098 (Python Code)

Max Activating Token Index: 368

Text #4

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0630. Min Act: -0.0003

Data Index: 1204587 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0636. Min Act: -0.0003

Data Index: 639659 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0593. Min Act: -0.0002

Data Index: 883110 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0631. Min Act: -0.0003

Data Index: 1152147 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0621. Min Act: -0.0003

Data Index: 1272026 (C4 (Web Text))

Max Activating Token Index: 599

Text #9

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0625. Min Act: -0.0003

Data Index: 34756 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0657. Min Act: -0.0003

Data Index: 1024116 (C4 (Web Text))

Max Activating Token Index: 966

Text #11

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0612. Min Act: -0.0003

Data Index: 749032 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0593. Min Act: -0.0003

Data Index: 1268608 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0627. Min Act: -0.0002

Data Index: 517720 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0564. Min Act: -0.0003

Data Index: 381271 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0573. Min Act: -0.0004

Data Index: 1241287 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0592. Min Act: -0.0003

Data Index: 769723 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0610. Min Act: -0.0003

Data Index: 1173639 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0599. Min Act: -0.0003

Data Index: 576706 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0614. Min Act: -0.0003

Data Index: 1010390 (C4 (Web Text))

Max Activating Token Index: 459