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

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

Neuron 4457 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: 0.0952. Min Range: -0.0952

Max Act: 0.0940. Min Act: -0.0002

Data Index: 1148464 (C4 (Web Text))

Max Activating Token Index: 371

Text #1

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0952. Min Act: -0.0002

Data Index: 102026 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0855. Min Act: -0.0002

Data Index: 1331484 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0852. Min Act: -0.0002

Data Index: 842361 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0776. Min Act: -0.0002

Data Index: 732175 (C4 (Web Text))

Max Activating Token Index: 352

Text #5

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0806. Min Act: -0.0002

Data Index: 32937 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0705. Min Act: -0.0002

Data Index: 545702 (C4 (Web Text))

Max Activating Token Index: 617

Text #7

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0769. Min Act: -0.0002

Data Index: 962702 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0797. Min Act: -0.0002

Data Index: 164376 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0815. Min Act: -0.0002

Data Index: 1010227 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0731. Min Act: -0.0002

Data Index: 496634 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0749. Min Act: -0.0002

Data Index: 1141635 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0755. Min Act: -0.0002

Data Index: 342570 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0747. Min Act: -0.0002

Data Index: 970698 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0765. Min Act: -0.0002

Data Index: 268003 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0735. Min Act: -0.0002

Data Index: 161423 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0716. Min Act: -0.0002

Data Index: 1214853 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0735. Min Act: -0.0002

Data Index: 237645 (C4 (Web Text))

Max Activating Token Index: 311

Text #18

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0687. Min Act: -0.0002

Data Index: 1134923 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0762. Min Act: -0.0002

Data Index: 409976 (C4 (Web Text))

Max Activating Token Index: 220