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

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

Neuron 4727 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4797. Min Range: -4.4797

Max Act: 4.3656. Min Act: -0.0000

Data Index: 486731 (C4 (Web Text))

Max Activating Token Index: 822

Text #1

Max Range: 4.4797. Min Range: -4.4797

Max Act: 4.3769. Min Act: -0.0000

Data Index: 378623 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 4.4797. Min Range: -4.4797

Max Act: 4.4797. Min Act: -0.0000

Data Index: 236559 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 4.4797. Min Range: -4.4797

Max Act: 4.4174. Min Act: -0.0000

Data Index: 1309080 (C4 (Web Text))

Max Activating Token Index: 544

Text #4

Max Range: 4.4797. Min Range: -4.4797

Max Act: 4.4036. Min Act: -0.0000

Data Index: 534166 (C4 (Web Text))

Max Activating Token Index: 952

Text #5

Max Range: 4.4797. Min Range: -4.4797

Max Act: 4.2816. Min Act: -0.0000

Data Index: 347182 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 4.4797. Min Range: -4.4797

Max Act: 4.3602. Min Act: 0.0000

Data Index: 561425 (C4 (Web Text))

Max Activating Token Index: 972

Text #7

Max Range: 4.4797. Min Range: -4.4797

Max Act: 3.9873. Min Act: -0.0000

Data Index: 107231 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 4.4797. Min Range: -4.4797

Max Act: 3.7869. Min Act: -0.0000

Data Index: 693928 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 4.4797. Min Range: -4.4797

Max Act: 4.0659. Min Act: -0.0000

Data Index: 249760 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 4.4797. Min Range: -4.4797

Max Act: 4.2153. Min Act: -0.0000

Data Index: 770497 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 4.4797. Min Range: -4.4797

Max Act: 4.3955. Min Act: -0.0000

Data Index: 39167 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 4.4797. Min Range: -4.4797

Max Act: 4.1558. Min Act: -0.0000

Data Index: 1137494 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 4.4797. Min Range: -4.4797

Max Act: 3.7955. Min Act: -0.0000

Data Index: 165568 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 4.4797. Min Range: -4.4797

Max Act: 3.8623. Min Act: -0.0000

Data Index: 317564 (C4 (Web Text))

Max Activating Token Index: 193

Text #15

Max Range: 4.4797. Min Range: -4.4797

Max Act: 3.6406. Min Act: -0.0000

Data Index: 1200673 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 4.4797. Min Range: -4.4797

Max Act: 3.9810. Min Act: -0.0000

Data Index: 256498 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 4.4797. Min Range: -4.4797

Max Act: 3.9550. Min Act: -0.0000

Data Index: 999546 (C4 (Web Text))

Max Activating Token Index: 259

Text #18

Max Range: 4.4797. Min Range: -4.4797

Max Act: 3.9495. Min Act: -0.0000

Data Index: 30110 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 4.4797. Min Range: -4.4797

Max Act: 3.9439. Min Act: -0.0000

Data Index: 437146 (C4 (Web Text))

Max Activating Token Index: 68