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

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

Neuron 3128 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0664. Min Act: -0.0001

Data Index: 752488 (C4 (Web Text))

Max Activating Token Index: 632

Text #1

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0660. Min Act: -0.0001

Data Index: 128293 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0563. Min Act: -0.0001

Data Index: 1019989 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0576. Min Act: -0.0001

Data Index: 1180740 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0573. Min Act: -0.0001

Data Index: 646609 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0547. Min Act: -0.0001

Data Index: 1304971 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0510. Min Act: -0.0001

Data Index: 363735 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0488. Min Act: -0.0001

Data Index: 1331383 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0525. Min Act: -0.0001

Data Index: 605039 (C4 (Web Text))

Max Activating Token Index: 465

Text #9

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0522. Min Act: -0.0001

Data Index: 1116601 (C4 (Web Text))

Max Activating Token Index: 531

Text #10

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0517. Min Act: -0.0001

Data Index: 1280245 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0499. Min Act: -0.0001

Data Index: 154667 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0551. Min Act: -0.0001

Data Index: 384965 (C4 (Web Text))

Max Activating Token Index: 496

Text #13

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0493. Min Act: -0.0001

Data Index: 693561 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0505. Min Act: -0.0001

Data Index: 128455 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0523. Min Act: -0.0001

Data Index: 684790 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0522. Min Act: -0.0001

Data Index: 255487 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0499. Min Act: -0.0001

Data Index: 1001111 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0500. Min Act: -0.0001

Data Index: 455602 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0475. Min Act: -0.0001

Data Index: 339934 (C4 (Web Text))

Max Activating Token Index: 543