Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 506 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.7998. Min Act: -0.0000

Data Index: 1020464 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.6627. Min Act: -0.0000

Data Index: 1281482 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.6324. Min Act: -0.0000

Data Index: 1522019 (Python Code)

Max Activating Token Index: 305

Text #3

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5639. Min Act: -0.0000

Data Index: 745378 (C4 (Web Text))

Max Activating Token Index: 796

Text #4

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5618. Min Act: -0.0000

Data Index: 1623457 (Python Code)

Max Activating Token Index: 420

Text #5

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5787. Min Act: -0.0000

Data Index: 1580990 (Python Code)

Max Activating Token Index: 327

Text #6

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5379. Min Act: -0.0000

Data Index: 1291445 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5311. Min Act: -0.0000

Data Index: 1028796 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5440. Min Act: -0.0000

Data Index: 1504881 (Python Code)

Max Activating Token Index: 595

Text #9

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5172. Min Act: -0.0000

Data Index: 814866 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5270. Min Act: -0.0000

Data Index: 1376020 (Python Code)

Max Activating Token Index: 909

Text #11

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5381. Min Act: -0.0000

Data Index: 219634 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5168. Min Act: -0.0000

Data Index: 1541258 (Python Code)

Max Activating Token Index: 794

Text #13

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.4962. Min Act: -0.0000

Data Index: 1378276 (Python Code)

Max Activating Token Index: 664

Text #14

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.4873. Min Act: -0.0000

Data Index: 1336217 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5087. Min Act: -0.0000

Data Index: 1602677 (Python Code)

Max Activating Token Index: 298

Text #16

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.4862. Min Act: -0.0000

Data Index: 1533943 (Python Code)

Max Activating Token Index: 464

Text #17

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.4927. Min Act: -0.0000

Data Index: 1466004 (Python Code)

Max Activating Token Index: 779

Text #18

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.4873. Min Act: -0.0000

Data Index: 624413 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.4621. Min Act: -0.0000

Data Index: 753495 (C4 (Web Text))

Max Activating Token Index: 659