Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1686 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0579. Min Act: -0.0003

Data Index: 1561356 (Python Code)

Max Activating Token Index: 280

Text #1

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0570. Min Act: -0.0004

Data Index: 1444494 (Python Code)

Max Activating Token Index: 812

Text #2

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0558. Min Act: -0.0003

Data Index: 849494 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0530. Min Act: -0.0003

Data Index: 833843 (C4 (Web Text))

Max Activating Token Index: 957

Text #4

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0514. Min Act: -0.0003

Data Index: 204166 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0512. Min Act: -0.0003

Data Index: 441099 (C4 (Web Text))

Max Activating Token Index: 305

Text #6

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0495. Min Act: -0.0003

Data Index: 25718 (C4 (Web Text))

Max Activating Token Index: 976

Text #7

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0503. Min Act: -0.0003

Data Index: 559815 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0485. Min Act: -0.0004

Data Index: 864608 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0485. Min Act: -0.0004

Data Index: 285503 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0471. Min Act: -0.0003

Data Index: 1165211 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0478. Min Act: -0.0004

Data Index: 486311 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0467. Min Act: -0.0004

Data Index: 31813 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0454. Min Act: -0.0003

Data Index: 669825 (C4 (Web Text))

Max Activating Token Index: 633

Text #14

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0483. Min Act: -0.0003

Data Index: 799711 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0463. Min Act: -0.0003

Data Index: 727120 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0463. Min Act: -0.0003

Data Index: 54526 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0454. Min Act: -0.0004

Data Index: 241176 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0469. Min Act: -0.0004

Data Index: 1165834 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0468. Min Act: -0.0003

Data Index: 77426 (C4 (Web Text))

Max Activating Token Index: 56