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

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

Neuron 503 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0664. Min Act: -0.0006

Data Index: 717587 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0635. Min Act: -0.0006

Data Index: 1222359 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0618. Min Act: -0.0006

Data Index: 435363 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0562. Min Act: -0.0006

Data Index: 648389 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0585. Min Act: -0.0006

Data Index: 1190030 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0595. Min Act: -0.0006

Data Index: 383849 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0574. Min Act: -0.0006

Data Index: 222100 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0563. Min Act: -0.0006

Data Index: 701085 (C4 (Web Text))

Max Activating Token Index: 754

Text #8

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0582. Min Act: -0.0006

Data Index: 1150283 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0545. Min Act: -0.0006

Data Index: 160430 (C4 (Web Text))

Max Activating Token Index: 458

Text #10

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0582. Min Act: -0.0006

Data Index: 1105928 (C4 (Web Text))

Max Activating Token Index: 797

Text #11

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0554. Min Act: -0.0006

Data Index: 425409 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0553. Min Act: -0.0006

Data Index: 39068 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0514. Min Act: -0.0005

Data Index: 288924 (C4 (Web Text))

Max Activating Token Index: 681

Text #14

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0543. Min Act: -0.0005

Data Index: 772568 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0554. Min Act: -0.0006

Data Index: 413686 (C4 (Web Text))

Max Activating Token Index: 237

Text #16

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0552. Min Act: -0.0006

Data Index: 266689 (C4 (Web Text))

Max Activating Token Index: 472

Text #17

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0532. Min Act: -0.0006

Data Index: 686000 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0541. Min Act: -0.0006

Data Index: 636825 (C4 (Web Text))

Max Activating Token Index: 874

Text #19

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0519. Min Act: -0.0006

Data Index: 852077 (C4 (Web Text))

Max Activating Token Index: 483