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

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

Neuron 3813 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0794. Min Act: -0.0002

Data Index: 1028920 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0659. Min Act: -0.0002

Data Index: 973123 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0577. Min Act: -0.0002

Data Index: 14036 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0548. Min Act: -0.0002

Data Index: 994107 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0525. Min Act: -0.0002

Data Index: 713498 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0527. Min Act: -0.0002

Data Index: 890077 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0522. Min Act: -0.0002

Data Index: 1041436 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0512. Min Act: -0.0002

Data Index: 79123 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0506. Min Act: -0.0002

Data Index: 800705 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0484. Min Act: -0.0002

Data Index: 837389 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0481. Min Act: -0.0002

Data Index: 748198 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0473. Min Act: -0.0002

Data Index: 673585 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0470. Min Act: -0.0002

Data Index: 760269 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0475. Min Act: -0.0002

Data Index: 965770 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0465. Min Act: -0.0002

Data Index: 500575 (C4 (Web Text))

Max Activating Token Index: 524

Text #15

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0447. Min Act: -0.0002

Data Index: 435158 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0467. Min Act: -0.0002

Data Index: 1293670 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0449. Min Act: -0.0002

Data Index: 155240 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0448. Min Act: -0.0002

Data Index: 231483 (C4 (Web Text))

Max Activating Token Index: 492

Text #19

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0451. Min Act: -0.0002

Data Index: 1025632 (C4 (Web Text))

Max Activating Token Index: 765