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

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

Neuron 1245 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0386. Min Act: -0.0004

Data Index: 88105 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0507. Min Act: -0.0004

Data Index: 427914 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0511. Min Act: -0.0004

Data Index: 216997 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0412. Min Act: -0.0004

Data Index: 126572 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0416. Min Act: -0.0004

Data Index: 953590 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0417. Min Act: -0.0004

Data Index: 435715 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0452. Min Act: -0.0004

Data Index: 490633 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0451. Min Act: -0.0004

Data Index: 70352 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0472. Min Act: -0.0004

Data Index: 184864 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0428. Min Act: -0.0004

Data Index: 119205 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0442. Min Act: -0.0004

Data Index: 727608 (C4 (Web Text))

Max Activating Token Index: 739

Text #11

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0471. Min Act: -0.0004

Data Index: 122532 (C4 (Web Text))

Max Activating Token Index: 627

Text #12

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0425. Min Act: -0.0004

Data Index: 625918 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0430. Min Act: -0.0004

Data Index: 630507 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0421. Min Act: -0.0004

Data Index: 285198 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0389. Min Act: -0.0004

Data Index: 816552 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0434. Min Act: -0.0004

Data Index: 776159 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0419. Min Act: -0.0004

Data Index: 691911 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0422. Min Act: -0.0004

Data Index: 102063 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0490. Min Act: -0.0004

Data Index: 325920 (C4 (Web Text))

Max Activating Token Index: 275