Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 867 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.5917. Min Act: -0.0003

Data Index: 801785 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.0775. Min Act: -0.0003

Data Index: 1443629 (Python Code)

Max Activating Token Index: 581

Text #2

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.0720. Min Act: -0.0003

Data Index: 649506 (C4 (Web Text))

Max Activating Token Index: 452

Text #3

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.0705. Min Act: -0.0002

Data Index: 150764 (C4 (Web Text))

Max Activating Token Index: 644

Text #4

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.0715. Min Act: -0.0003

Data Index: 1638575 (Python Code)

Max Activating Token Index: 299

Text #5

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.0591. Min Act: -0.0003

Data Index: 1263456 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.0609. Min Act: -0.0002

Data Index: 186382 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.0570. Min Act: -0.0003

Data Index: 833839 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.0525. Min Act: -0.0003

Data Index: 1635559 (Python Code)

Max Activating Token Index: 798

Text #9

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.0528. Min Act: -0.0002

Data Index: 1221273 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.0557. Min Act: -0.0003

Data Index: 1499797 (Python Code)

Max Activating Token Index: 834

Text #11

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.0504. Min Act: -0.0003

Data Index: 963132 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.0371. Min Act: -0.0003

Data Index: 1514374 (Python Code)

Max Activating Token Index: 424

Text #13

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.0465. Min Act: -0.0003

Data Index: 267378 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.0446. Min Act: -0.0003

Data Index: 1092912 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.0367. Min Act: -0.0003

Data Index: 1503312 (Python Code)

Max Activating Token Index: 993

Text #16

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.0360. Min Act: -0.0003

Data Index: 1542660 (Python Code)

Max Activating Token Index: 942

Text #17

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.0412. Min Act: -0.0002

Data Index: 738787 (C4 (Web Text))

Max Activating Token Index: 280

Text #18

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.0362. Min Act: -0.0003

Data Index: 139582 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.0357. Min Act: -0.0003

Data Index: 884225 (C4 (Web Text))

Max Activating Token Index: 391