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

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

Neuron 3772 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0120. Min Range: -1.0120

Max Act: 1.0120. Min Act: -0.0001

Data Index: 1294925 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 1.0120. Min Range: -1.0120

Max Act: 0.8936. Min Act: -0.0001

Data Index: 392388 (C4 (Web Text))

Max Activating Token Index: 275

Text #2

Max Range: 1.0120. Min Range: -1.0120

Max Act: 0.9182. Min Act: -0.0001

Data Index: 73797 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 1.0120. Min Range: -1.0120

Max Act: 0.8646. Min Act: -0.0001

Data Index: 1187963 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 1.0120. Min Range: -1.0120

Max Act: 0.8197. Min Act: -0.0001

Data Index: 67848 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 1.0120. Min Range: -1.0120

Max Act: 0.8697. Min Act: -0.0001

Data Index: 1143514 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 1.0120. Min Range: -1.0120

Max Act: 0.8424. Min Act: -0.0001

Data Index: 1109257 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 1.0120. Min Range: -1.0120

Max Act: 0.7381. Min Act: -0.0001

Data Index: 699853 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 1.0120. Min Range: -1.0120

Max Act: 0.6790. Min Act: -0.0001

Data Index: 1086758 (C4 (Web Text))

Max Activating Token Index: 196

Text #9

Max Range: 1.0120. Min Range: -1.0120

Max Act: 0.7288. Min Act: -0.0001

Data Index: 120845 (C4 (Web Text))

Max Activating Token Index: 749

Text #10

Max Range: 1.0120. Min Range: -1.0120

Max Act: 0.6864. Min Act: -0.0001

Data Index: 1105048 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 1.0120. Min Range: -1.0120

Max Act: 0.7269. Min Act: -0.0001

Data Index: 71629 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 1.0120. Min Range: -1.0120

Max Act: 0.7578. Min Act: -0.0001

Data Index: 707117 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 1.0120. Min Range: -1.0120

Max Act: 0.7578. Min Act: -0.0001

Data Index: 1349336 (C4 (Web Text))

Max Activating Token Index: 462

Text #14

Max Range: 1.0120. Min Range: -1.0120

Max Act: 0.7310. Min Act: -0.0001

Data Index: 291070 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 1.0120. Min Range: -1.0120

Max Act: 0.7428. Min Act: -0.0001

Data Index: 1319409 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 1.0120. Min Range: -1.0120

Max Act: 0.7668. Min Act: -0.0001

Data Index: 635031 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 1.0120. Min Range: -1.0120

Max Act: 0.7768. Min Act: -0.0001

Data Index: 617019 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 1.0120. Min Range: -1.0120

Max Act: 0.6943. Min Act: -0.0001

Data Index: 149412 (C4 (Web Text))

Max Activating Token Index: 787

Text #19

Max Range: 1.0120. Min Range: -1.0120

Max Act: 0.6799. Min Act: -0.0001

Data Index: 258567 (C4 (Web Text))

Max Activating Token Index: 665