Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1783 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0780. Min Act: -0.0001

Data Index: 549678 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0899. Min Act: -0.0001

Data Index: 127665 (C4 (Web Text))

Max Activating Token Index: 490

Text #2

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0883. Min Act: -0.0001

Data Index: 54665 (C4 (Web Text))

Max Activating Token Index: 354

Text #3

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0898. Min Act: -0.0001

Data Index: 121969 (C4 (Web Text))

Max Activating Token Index: 829

Text #4

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.1252. Min Act: -0.0001

Data Index: 1091349 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0812. Min Act: -0.0001

Data Index: 846843 (C4 (Web Text))

Max Activating Token Index: 442

Text #6

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0597. Min Act: -0.0001

Data Index: 147124 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0718. Min Act: -0.0001

Data Index: 114102 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0724. Min Act: -0.0001

Data Index: 286091 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0685. Min Act: -0.0001

Data Index: 396547 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0821. Min Act: -0.0001

Data Index: 1112350 (C4 (Web Text))

Max Activating Token Index: 172

Text #11

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0705. Min Act: -0.0001

Data Index: 11747 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0704. Min Act: -0.0001

Data Index: 991531 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0797. Min Act: -0.0001

Data Index: 71843 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0806. Min Act: -0.0001

Data Index: 900278 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0598. Min Act: -0.0001

Data Index: 283691 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0661. Min Act: -0.0001

Data Index: 1121343 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0636. Min Act: -0.0001

Data Index: 610455 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0742. Min Act: -0.0001

Data Index: 13102 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 0.1252. Min Range: -0.1252

Max Act: 0.0563. Min Act: -0.0001

Data Index: 87357 (C4 (Web Text))

Max Activating Token Index: 91