Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 376 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0681. Min Act: -0.0001

Data Index: 632371 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0635. Min Act: -0.0001

Data Index: 1444723 (Python Code)

Max Activating Token Index: 309

Text #2

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0688. Min Act: -0.0001

Data Index: 1590529 (Python Code)

Max Activating Token Index: 730

Text #3

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0651. Min Act: -0.0001

Data Index: 192182 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0661. Min Act: -0.0001

Data Index: 818793 (C4 (Web Text))

Max Activating Token Index: 981

Text #5

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0671. Min Act: -0.0001

Data Index: 890875 (C4 (Web Text))

Max Activating Token Index: 791

Text #6

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0590. Min Act: -0.0001

Data Index: 1297631 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0596. Min Act: -0.0001

Data Index: 1512901 (Python Code)

Max Activating Token Index: 476

Text #8

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0578. Min Act: -0.0001

Data Index: 358977 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0577. Min Act: -0.0001

Data Index: 691961 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0546. Min Act: -0.0001

Data Index: 454405 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0565. Min Act: -0.0001

Data Index: 620774 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0554. Min Act: -0.0001

Data Index: 466595 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0576. Min Act: -0.0000

Data Index: 860655 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0544. Min Act: -0.0001

Data Index: 1246761 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0515. Min Act: -0.0001

Data Index: 835460 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0540. Min Act: -0.0001

Data Index: 1432085 (Python Code)

Max Activating Token Index: 119

Text #17

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0556. Min Act: -0.0001

Data Index: 78227 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0545. Min Act: -0.0001

Data Index: 1491055 (Python Code)

Max Activating Token Index: 221

Text #19

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0536. Min Act: -0.0001

Data Index: 909628 (C4 (Web Text))

Max Activating Token Index: 340