Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6109 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.7701. Min Act: -0.0001

Data Index: 379687 (C4 (Web Text))

Max Activating Token Index: 620

Text #1

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.6281. Min Act: -0.0001

Data Index: 1048797 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.5944. Min Act: -0.0001

Data Index: 1337801 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.5712. Min Act: -0.0001

Data Index: 1097393 (C4 (Web Text))

Max Activating Token Index: 548

Text #4

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.5466. Min Act: -0.0001

Data Index: 1175540 (C4 (Web Text))

Max Activating Token Index: 869

Text #5

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.5617. Min Act: -0.0001

Data Index: 67680 (C4 (Web Text))

Max Activating Token Index: 653

Text #6

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.5770. Min Act: -0.0001

Data Index: 1005980 (C4 (Web Text))

Max Activating Token Index: 1009

Text #7

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.5901. Min Act: -0.0001

Data Index: 972393 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.5809. Min Act: -0.0001

Data Index: 455426 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.4956. Min Act: -0.0001

Data Index: 937548 (C4 (Web Text))

Max Activating Token Index: 858

Text #10

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.5486. Min Act: -0.0001

Data Index: 947629 (C4 (Web Text))

Max Activating Token Index: 703

Text #11

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.5589. Min Act: -0.0001

Data Index: 1143059 (C4 (Web Text))

Max Activating Token Index: 468

Text #12

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.4909. Min Act: -0.0001

Data Index: 607603 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.4990. Min Act: -0.0001

Data Index: 528863 (C4 (Web Text))

Max Activating Token Index: 937

Text #14

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.6205. Min Act: -0.0001

Data Index: 1487735 (Python Code)

Max Activating Token Index: 912

Text #15

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.5006. Min Act: -0.0001

Data Index: 292687 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.5293. Min Act: -0.0001

Data Index: 884641 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.4963. Min Act: -0.0001

Data Index: 924733 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.4727. Min Act: -0.0001

Data Index: 38209 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 0.7701. Min Range: -0.7701

Max Act: 0.5039. Min Act: -0.0001

Data Index: 149077 (C4 (Web Text))

Max Activating Token Index: 515