Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 993 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0731. Min Act: -0.0002

Data Index: 1305869 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0675. Min Act: -0.0001

Data Index: 691817 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0667. Min Act: -0.0002

Data Index: 1225570 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0654. Min Act: -0.0002

Data Index: 673320 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0660. Min Act: -0.0002

Data Index: 742931 (C4 (Web Text))

Max Activating Token Index: 404

Text #5

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0636. Min Act: -0.0001

Data Index: 47590 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0626. Min Act: -0.0001

Data Index: 908505 (C4 (Web Text))

Max Activating Token Index: 439

Text #7

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0658. Min Act: -0.0001

Data Index: 1205208 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0629. Min Act: -0.0002

Data Index: 1111773 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0640. Min Act: -0.0002

Data Index: 817841 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0627. Min Act: -0.0001

Data Index: 174061 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0608. Min Act: -0.0001

Data Index: 537390 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0607. Min Act: -0.0002

Data Index: 288344 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0623. Min Act: -0.0001

Data Index: 523877 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0596. Min Act: -0.0002

Data Index: 946412 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0616. Min Act: -0.0001

Data Index: 654551 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0613. Min Act: -0.0002

Data Index: 1248962 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0601. Min Act: -0.0001

Data Index: 1352018 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0628. Min Act: -0.0002

Data Index: 285618 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0586. Min Act: -0.0002

Data Index: 644420 (C4 (Web Text))

Max Activating Token Index: 678