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

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

Neuron 3611 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0940. Min Range: -1.0940

Max Act: 1.0940. Min Act: -0.0000

Data Index: 645395 (C4 (Web Text))

Max Activating Token Index: 407

Text #1

Max Range: 1.0940. Min Range: -1.0940

Max Act: 1.0214. Min Act: -0.0000

Data Index: 138171 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 1.0940. Min Range: -1.0940

Max Act: 0.9688. Min Act: -0.0000

Data Index: 89315 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 1.0940. Min Range: -1.0940

Max Act: 0.9438. Min Act: -0.0000

Data Index: 50200 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 1.0940. Min Range: -1.0940

Max Act: 0.9294. Min Act: -0.0000

Data Index: 1113195 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 1.0940. Min Range: -1.0940

Max Act: 0.9098. Min Act: -0.0000

Data Index: 869029 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 1.0940. Min Range: -1.0940

Max Act: 0.9236. Min Act: -0.0000

Data Index: 876414 (C4 (Web Text))

Max Activating Token Index: 371

Text #7

Max Range: 1.0940. Min Range: -1.0940

Max Act: 0.8721. Min Act: -0.0000

Data Index: 1280854 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 1.0940. Min Range: -1.0940

Max Act: 0.8087. Min Act: -0.0000

Data Index: 407436 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 1.0940. Min Range: -1.0940

Max Act: 0.8390. Min Act: -0.0000

Data Index: 651504 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 1.0940. Min Range: -1.0940

Max Act: 0.8558. Min Act: -0.0000

Data Index: 72067 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 1.0940. Min Range: -1.0940

Max Act: 0.8513. Min Act: -0.0000

Data Index: 509860 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 1.0940. Min Range: -1.0940

Max Act: 0.8452. Min Act: -0.0000

Data Index: 1288516 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 1.0940. Min Range: -1.0940

Max Act: 0.8740. Min Act: -0.0000

Data Index: 443141 (C4 (Web Text))

Max Activating Token Index: 510

Text #14

Max Range: 1.0940. Min Range: -1.0940

Max Act: 0.8658. Min Act: -0.0000

Data Index: 559118 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 1.0940. Min Range: -1.0940

Max Act: 0.8713. Min Act: -0.0000

Data Index: 1289740 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 1.0940. Min Range: -1.0940

Max Act: 0.7791. Min Act: -0.0000

Data Index: 4333 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 1.0940. Min Range: -1.0940

Max Act: 0.8932. Min Act: -0.0000

Data Index: 662065 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 1.0940. Min Range: -1.0940

Max Act: 0.7807. Min Act: -0.0000

Data Index: 468974 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 1.0940. Min Range: -1.0940

Max Act: 0.9791. Min Act: -0.0000

Data Index: 1027337 (C4 (Web Text))

Max Activating Token Index: 583