Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 19 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0724. Min Act: -0.0003

Data Index: 599225 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0741. Min Act: -0.0004

Data Index: 19628 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0708. Min Act: -0.0003

Data Index: 326934 (C4 (Web Text))

Max Activating Token Index: 845

Text #3

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0687. Min Act: -0.0004

Data Index: 487991 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0678. Min Act: -0.0003

Data Index: 739790 (C4 (Web Text))

Max Activating Token Index: 898

Text #5

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0682. Min Act: -0.0003

Data Index: 37941 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0689. Min Act: -0.0003

Data Index: 1290447 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0642. Min Act: -0.0002

Data Index: 1005739 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0626. Min Act: -0.0003

Data Index: 813219 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0637. Min Act: -0.0003

Data Index: 1225458 (C4 (Web Text))

Max Activating Token Index: 536

Text #10

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0632. Min Act: -0.0003

Data Index: 889367 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0626. Min Act: -0.0003

Data Index: 838714 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0618. Min Act: -0.0003

Data Index: 551332 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0620. Min Act: -0.0002

Data Index: 179453 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0602. Min Act: -0.0003

Data Index: 1124895 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0610. Min Act: -0.0002

Data Index: 541350 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0602. Min Act: -0.0003

Data Index: 466203 (C4 (Web Text))

Max Activating Token Index: 665

Text #17

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0614. Min Act: -0.0002

Data Index: 1072828 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0602. Min Act: -0.0002

Data Index: 1149988 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0601. Min Act: -0.0002

Data Index: 1305636 (C4 (Web Text))

Max Activating Token Index: 374