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

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

Neuron 1922 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: 0.0689. Min Range: -0.0689

Max Act: 0.0679. Min Act: -0.0003

Data Index: 729372 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0679. Min Act: -0.0004

Data Index: 121810 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0689. Min Act: -0.0003

Data Index: 1252061 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0644. Min Act: -0.0003

Data Index: 763782 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0623. Min Act: -0.0003

Data Index: 670049 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0635. Min Act: -0.0003

Data Index: 605456 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0620. Min Act: -0.0003

Data Index: 1067811 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0591. Min Act: -0.0002

Data Index: 895479 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0613. Min Act: -0.0003

Data Index: 87866 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0602. Min Act: -0.0003

Data Index: 577598 (C4 (Web Text))

Max Activating Token Index: 402

Text #10

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0599. Min Act: -0.0003

Data Index: 1097706 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0607. Min Act: -0.0003

Data Index: 158512 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0601. Min Act: -0.0003

Data Index: 1061582 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0623. Min Act: -0.0004

Data Index: 675064 (C4 (Web Text))

Max Activating Token Index: 405

Text #14

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0596. Min Act: -0.0003

Data Index: 923102 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0595. Min Act: -0.0003

Data Index: 1252600 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0581. Min Act: -0.0004

Data Index: 756076 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0589. Min Act: -0.0003

Data Index: 532786 (C4 (Web Text))

Max Activating Token Index: 351

Text #18

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0606. Min Act: -0.0003

Data Index: 1064341 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0568. Min Act: -0.0003

Data Index: 512249 (C4 (Web Text))

Max Activating Token Index: 532