Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 644 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.3642. Min Act: -0.0001

Data Index: 1238484 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.3455. Min Act: -0.0000

Data Index: 734265 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.3235. Min Act: -0.0000

Data Index: 192955 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.3054. Min Act: -0.0000

Data Index: 180263 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.3214. Min Act: -0.0000

Data Index: 827393 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.3091. Min Act: -0.0001

Data Index: 1227993 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2888. Min Act: -0.0000

Data Index: 1343175 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2747. Min Act: -0.0000

Data Index: 795180 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2689. Min Act: -0.0000

Data Index: 760018 (C4 (Web Text))

Max Activating Token Index: 992

Text #9

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2669. Min Act: -0.0001

Data Index: 224594 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2706. Min Act: -0.0000

Data Index: 1198456 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2604. Min Act: -0.0001

Data Index: 853556 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2609. Min Act: -0.0000

Data Index: 88412 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2600. Min Act: -0.0001

Data Index: 1254890 (C4 (Web Text))

Max Activating Token Index: 202

Text #14

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2511. Min Act: -0.0000

Data Index: 471783 (C4 (Web Text))

Max Activating Token Index: 740

Text #15

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2513. Min Act: -0.0000

Data Index: 549342 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2659. Min Act: -0.0000

Data Index: 783357 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2648. Min Act: -0.0000

Data Index: 643879 (C4 (Web Text))

Max Activating Token Index: 173

Text #18

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2467. Min Act: -0.0000

Data Index: 816046 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 0.3642. Min Range: -0.3642

Max Act: 0.2636. Min Act: -0.0000

Data Index: 866041 (C4 (Web Text))

Max Activating Token Index: 992