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

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

Neuron 842 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0490. Min Act: -0.0004

Data Index: 186949 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0453. Min Act: -0.0004

Data Index: 1355317 (C4 (Web Text))

Max Activating Token Index: 490

Text #2

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0467. Min Act: -0.0005

Data Index: 1536213 (Python Code)

Max Activating Token Index: 775

Text #3

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0470. Min Act: -0.0004

Data Index: 1031124 (C4 (Web Text))

Max Activating Token Index: 420

Text #4

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0420. Min Act: -0.0004

Data Index: 606738 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0417. Min Act: -0.0005

Data Index: 288319 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0448. Min Act: -0.0005

Data Index: 799537 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0460. Min Act: -0.0005

Data Index: 1449818 (Python Code)

Max Activating Token Index: 440

Text #8

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0447. Min Act: -0.0004

Data Index: 325573 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0430. Min Act: -0.0004

Data Index: 521861 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0446. Min Act: -0.0004

Data Index: 692862 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0434. Min Act: -0.0004

Data Index: 1007079 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0440. Min Act: -0.0004

Data Index: 677069 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0440. Min Act: -0.0005

Data Index: 814568 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0425. Min Act: -0.0004

Data Index: 160265 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0433. Min Act: -0.0004

Data Index: 920473 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0438. Min Act: -0.0004

Data Index: 217565 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0412. Min Act: -0.0004

Data Index: 1128103 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0442. Min Act: -0.0004

Data Index: 816807 (C4 (Web Text))

Max Activating Token Index: 607

Text #19

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0433. Min Act: -0.0004

Data Index: 1327828 (C4 (Web Text))

Max Activating Token Index: 705