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

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

Neuron 2539 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: 3.6633. Min Range: -3.6633

Max Act: 3.6633. Min Act: -0.0000

Data Index: 163317 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 3.6633. Min Range: -3.6633

Max Act: 3.2800. Min Act: -0.0000

Data Index: 1122917 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 3.6633. Min Range: -3.6633

Max Act: 3.4482. Min Act: -0.0000

Data Index: 949616 (C4 (Web Text))

Max Activating Token Index: 642

Text #3

Max Range: 3.6633. Min Range: -3.6633

Max Act: 2.9539. Min Act: -0.0000

Data Index: 1077980 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 3.6633. Min Range: -3.6633

Max Act: 2.9666. Min Act: -0.0001

Data Index: 1159695 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 3.6633. Min Range: -3.6633

Max Act: 2.6786. Min Act: -0.0000

Data Index: 893831 (C4 (Web Text))

Max Activating Token Index: 501

Text #6

Max Range: 3.6633. Min Range: -3.6633

Max Act: 2.6897. Min Act: -0.0000

Data Index: 992293 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 3.6633. Min Range: -3.6633

Max Act: 2.5677. Min Act: -0.0000

Data Index: 1245916 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 3.6633. Min Range: -3.6633

Max Act: 2.1568. Min Act: -0.0000

Data Index: 110400 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 3.6633. Min Range: -3.6633

Max Act: 1.9327. Min Act: -0.0000

Data Index: 382328 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 3.6633. Min Range: -3.6633

Max Act: 2.2448. Min Act: -0.0000

Data Index: 51772 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 3.6633. Min Range: -3.6633

Max Act: 1.9368. Min Act: -0.0000

Data Index: 746727 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 3.6633. Min Range: -3.6633

Max Act: 1.8449. Min Act: -0.0000

Data Index: 11548 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 3.6633. Min Range: -3.6633

Max Act: 1.8580. Min Act: -0.0001

Data Index: 1094867 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 3.6633. Min Range: -3.6633

Max Act: 1.9494. Min Act: -0.0000

Data Index: 718826 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 3.6633. Min Range: -3.6633

Max Act: 1.9519. Min Act: -0.0000

Data Index: 132989 (C4 (Web Text))

Max Activating Token Index: 712

Text #16

Max Range: 3.6633. Min Range: -3.6633

Max Act: 1.5181. Min Act: -0.0000

Data Index: 539773 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 3.6633. Min Range: -3.6633

Max Act: 1.6075. Min Act: -0.0000

Data Index: 916536 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 3.6633. Min Range: -3.6633

Max Act: 1.6433. Min Act: -0.0000

Data Index: 55930 (C4 (Web Text))

Max Activating Token Index: 1022

Text #19

Max Range: 3.6633. Min Range: -3.6633

Max Act: 1.7284. Min Act: -0.0000

Data Index: 997526 (C4 (Web Text))

Max Activating Token Index: 704