Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3484 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0695. Min Act: -0.0002

Data Index: 1041612 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0721. Min Act: -0.0002

Data Index: 718059 (C4 (Web Text))

Max Activating Token Index: 386

Text #2

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0633. Min Act: -0.0002

Data Index: 636800 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0635. Min Act: -0.0002

Data Index: 500446 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0651. Min Act: -0.0002

Data Index: 217102 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0606. Min Act: -0.0002

Data Index: 410510 (C4 (Web Text))

Max Activating Token Index: 939

Text #6

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0603. Min Act: -0.0002

Data Index: 149870 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0583. Min Act: -0.0002

Data Index: 36022 (C4 (Web Text))

Max Activating Token Index: 676

Text #8

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0532. Min Act: -0.0002

Data Index: 430171 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0612. Min Act: -0.0002

Data Index: 1082064 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0544. Min Act: -0.0002

Data Index: 71743 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0564. Min Act: -0.0002

Data Index: 615407 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0574. Min Act: -0.0002

Data Index: 508960 (C4 (Web Text))

Max Activating Token Index: 833

Text #13

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0537. Min Act: -0.0002

Data Index: 1324411 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0533. Min Act: -0.0002

Data Index: 520989 (C4 (Web Text))

Max Activating Token Index: 695

Text #15

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0587. Min Act: -0.0002

Data Index: 602119 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0512. Min Act: -0.0002

Data Index: 1259678 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0484. Min Act: -0.0002

Data Index: 612994 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0519. Min Act: -0.0002

Data Index: 878116 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0534. Min Act: -0.0002

Data Index: 842718 (C4 (Web Text))

Max Activating Token Index: 407