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

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

Neuron 5194 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0759. Min Act: -0.0001

Data Index: 115677 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0659. Min Act: -0.0001

Data Index: 1175810 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0602. Min Act: -0.0001

Data Index: 1059083 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0534. Min Act: -0.0001

Data Index: 532087 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0529. Min Act: -0.0001

Data Index: 33279 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0554. Min Act: -0.0001

Data Index: 149090 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0514. Min Act: -0.0001

Data Index: 984503 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0558. Min Act: -0.0001

Data Index: 587790 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0500. Min Act: -0.0001

Data Index: 505730 (C4 (Web Text))

Max Activating Token Index: 410

Text #9

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0526. Min Act: -0.0001

Data Index: 731076 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0585. Min Act: -0.0001

Data Index: 865214 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0525. Min Act: -0.0001

Data Index: 1323332 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0526. Min Act: -0.0001

Data Index: 173685 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0537. Min Act: -0.0001

Data Index: 1376671 (Python Code)

Max Activating Token Index: 27

Text #14

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0534. Min Act: -0.0001

Data Index: 74590 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0482. Min Act: -0.0001

Data Index: 1038813 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0511. Min Act: -0.0001

Data Index: 1301156 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0530. Min Act: -0.0001

Data Index: 1530006 (Python Code)

Max Activating Token Index: 433

Text #18

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0504. Min Act: -0.0001

Data Index: 665986 (C4 (Web Text))

Max Activating Token Index: 198

Text #19

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0511. Min Act: -0.0001

Data Index: 1352990 (C4 (Web Text))

Max Activating Token Index: 965