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

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

Neuron 4460 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6877. Min Range: -2.6877

Max Act: 2.6877. Min Act: -0.0000

Data Index: 1305711 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 2.6877. Min Range: -2.6877

Max Act: 2.6660. Min Act: -0.0000

Data Index: 379887 (C4 (Web Text))

Max Activating Token Index: 532

Text #2

Max Range: 2.6877. Min Range: -2.6877

Max Act: 2.5613. Min Act: -0.0000

Data Index: 1117369 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 2.6877. Min Range: -2.6877

Max Act: 2.1233. Min Act: -0.0000

Data Index: 1188547 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 2.6877. Min Range: -2.6877

Max Act: 2.0964. Min Act: -0.0000

Data Index: 261066 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 2.6877. Min Range: -2.6877

Max Act: 2.0100. Min Act: -0.0000

Data Index: 553896 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 2.6877. Min Range: -2.6877

Max Act: 1.9906. Min Act: -0.0000

Data Index: 187196 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 2.6877. Min Range: -2.6877

Max Act: 1.9571. Min Act: -0.0000

Data Index: 14961 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 2.6877. Min Range: -2.6877

Max Act: 1.8468. Min Act: -0.0000

Data Index: 475482 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 2.6877. Min Range: -2.6877

Max Act: 1.9500. Min Act: -0.0000

Data Index: 1171490 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 2.6877. Min Range: -2.6877

Max Act: 1.7331. Min Act: -0.0000

Data Index: 1060604 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 2.6877. Min Range: -2.6877

Max Act: 1.8183. Min Act: -0.0000

Data Index: 1112017 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 2.6877. Min Range: -2.6877

Max Act: 1.7970. Min Act: -0.0000

Data Index: 1116137 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 2.6877. Min Range: -2.6877

Max Act: 1.6866. Min Act: -0.0000

Data Index: 98700 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 2.6877. Min Range: -2.6877

Max Act: 1.7796. Min Act: -0.0000

Data Index: 1093457 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 2.6877. Min Range: -2.6877

Max Act: 1.8762. Min Act: -0.0000

Data Index: 582103 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 2.6877. Min Range: -2.6877

Max Act: 1.7562. Min Act: -0.0000

Data Index: 506861 (C4 (Web Text))

Max Activating Token Index: 454

Text #17

Max Range: 2.6877. Min Range: -2.6877

Max Act: 1.7513. Min Act: -0.0000

Data Index: 13821 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 2.6877. Min Range: -2.6877

Max Act: 1.8637. Min Act: -0.0000

Data Index: 209223 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 2.6877. Min Range: -2.6877

Max Act: 1.6441. Min Act: -0.0000

Data Index: 880608 (C4 (Web Text))

Max Activating Token Index: 608