Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2815 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3954. Min Range: -1.3954

Max Act: 1.2722. Min Act: -0.0002

Data Index: 649032 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 1.3954. Min Range: -1.3954

Max Act: 1.3211. Min Act: -0.0002

Data Index: 355421 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 1.3954. Min Range: -1.3954

Max Act: 1.1698. Min Act: -0.0002

Data Index: 1142402 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 1.3954. Min Range: -1.3954

Max Act: 1.3954. Min Act: -0.0002

Data Index: 57519 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 1.3954. Min Range: -1.3954

Max Act: 1.3261. Min Act: -0.0002

Data Index: 526939 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 1.3954. Min Range: -1.3954

Max Act: 1.1747. Min Act: -0.0002

Data Index: 317378 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 1.3954. Min Range: -1.3954

Max Act: 1.0631. Min Act: -0.0002

Data Index: 532530 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 1.3954. Min Range: -1.3954

Max Act: 1.1730. Min Act: -0.0002

Data Index: 801291 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 1.3954. Min Range: -1.3954

Max Act: 1.0712. Min Act: -0.0002

Data Index: 720377 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 1.3954. Min Range: -1.3954

Max Act: 0.8914. Min Act: -0.0002

Data Index: 321840 (C4 (Web Text))

Max Activating Token Index: 858

Text #10

Max Range: 1.3954. Min Range: -1.3954

Max Act: 1.1209. Min Act: -0.0002

Data Index: 407062 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 1.3954. Min Range: -1.3954

Max Act: 1.1965. Min Act: -0.0002

Data Index: 313163 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 1.3954. Min Range: -1.3954

Max Act: 1.0583. Min Act: -0.0002

Data Index: 63303 (C4 (Web Text))

Max Activating Token Index: 378

Text #13

Max Range: 1.3954. Min Range: -1.3954

Max Act: 0.9724. Min Act: -0.0002

Data Index: 385028 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 1.3954. Min Range: -1.3954

Max Act: 0.9593. Min Act: -0.0002

Data Index: 932473 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 1.3954. Min Range: -1.3954

Max Act: 1.0445. Min Act: -0.0002

Data Index: 520055 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 1.3954. Min Range: -1.3954

Max Act: 1.0523. Min Act: -0.0002

Data Index: 1261640 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 1.3954. Min Range: -1.3954

Max Act: 1.0686. Min Act: -0.0002

Data Index: 1052171 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 1.3954. Min Range: -1.3954

Max Act: 1.0056. Min Act: -0.0002

Data Index: 281918 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 1.3954. Min Range: -1.3954

Max Act: 1.0604. Min Act: -0.0002

Data Index: 955548 (C4 (Web Text))

Max Activating Token Index: 171