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

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

Neuron 1540 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: 0.0754. Min Range: -0.0754

Max Act: 0.0754. Min Act: -0.0003

Data Index: 78121 (C4 (Web Text))

Max Activating Token Index: 667

Text #1

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0728. Min Act: -0.0003

Data Index: 1300260 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0721. Min Act: -0.0002

Data Index: 804504 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0686. Min Act: -0.0003

Data Index: 662234 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0683. Min Act: -0.0003

Data Index: 742363 (C4 (Web Text))

Max Activating Token Index: 942

Text #5

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0649. Min Act: -0.0003

Data Index: 887591 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0656. Min Act: -0.0003

Data Index: 216201 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0646. Min Act: -0.0003

Data Index: 1129701 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0626. Min Act: -0.0003

Data Index: 17612 (C4 (Web Text))

Max Activating Token Index: 577

Text #9

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0605. Min Act: -0.0003

Data Index: 479054 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0635. Min Act: -0.0003

Data Index: 268518 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0605. Min Act: -0.0003

Data Index: 265704 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0621. Min Act: -0.0003

Data Index: 1208402 (C4 (Web Text))

Max Activating Token Index: 520

Text #13

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0610. Min Act: -0.0003

Data Index: 835997 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0630. Min Act: -0.0003

Data Index: 950404 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0614. Min Act: -0.0003

Data Index: 291359 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0630. Min Act: -0.0004

Data Index: 447156 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0597. Min Act: -0.0003

Data Index: 230995 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0597. Min Act: -0.0003

Data Index: 1235210 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0595. Min Act: -0.0003

Data Index: 513405 (C4 (Web Text))

Max Activating Token Index: 869