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

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

Neuron 358 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: 0.0784. Min Range: -0.0784

Max Act: 0.0784. Min Act: -0.0003

Data Index: 1101790 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0757. Min Act: -0.0003

Data Index: 313644 (C4 (Web Text))

Max Activating Token Index: 522

Text #2

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0722. Min Act: -0.0003

Data Index: 409502 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0666. Min Act: -0.0003

Data Index: 1200455 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0683. Min Act: -0.0003

Data Index: 280136 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0664. Min Act: -0.0003

Data Index: 41822 (C4 (Web Text))

Max Activating Token Index: 623

Text #6

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0646. Min Act: -0.0003

Data Index: 712841 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0623. Min Act: -0.0003

Data Index: 449716 (C4 (Web Text))

Max Activating Token Index: 892

Text #8

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0640. Min Act: -0.0003

Data Index: 450606 (C4 (Web Text))

Max Activating Token Index: 944

Text #9

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0623. Min Act: -0.0003

Data Index: 1205179 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0604. Min Act: -0.0003

Data Index: 113410 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0644. Min Act: -0.0003

Data Index: 719919 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0575. Min Act: -0.0003

Data Index: 721005 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0604. Min Act: -0.0003

Data Index: 213270 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0620. Min Act: -0.0003

Data Index: 991547 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0577. Min Act: -0.0003

Data Index: 101848 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0571. Min Act: -0.0003

Data Index: 505068 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0577. Min Act: -0.0003

Data Index: 341389 (C4 (Web Text))

Max Activating Token Index: 54

Text #18

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0585. Min Act: -0.0004

Data Index: 1136587 (C4 (Web Text))

Max Activating Token Index: 445

Text #19

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0568. Min Act: -0.0003

Data Index: 778593 (C4 (Web Text))

Max Activating Token Index: 665