Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2066 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.5029. Min Act: -0.0000

Data Index: 611459 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.5062. Min Act: -0.0000

Data Index: 74592 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.4850. Min Act: -0.0000

Data Index: 725107 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.5000. Min Act: -0.0000

Data Index: 687465 (C4 (Web Text))

Max Activating Token Index: 776

Text #4

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.4505. Min Act: -0.0000

Data Index: 372531 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.4376. Min Act: -0.0000

Data Index: 995273 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.4423. Min Act: -0.0000

Data Index: 1204224 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.4281. Min Act: -0.0000

Data Index: 656126 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.4053. Min Act: -0.0000

Data Index: 1066056 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.3860. Min Act: -0.0000

Data Index: 453642 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.4116. Min Act: -0.0000

Data Index: 670461 (C4 (Web Text))

Max Activating Token Index: 953

Text #11

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.4042. Min Act: -0.0000

Data Index: 102631 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.3899. Min Act: -0.0000

Data Index: 1278104 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.4131. Min Act: -0.0000

Data Index: 496054 (C4 (Web Text))

Max Activating Token Index: 332

Text #14

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.3749. Min Act: -0.0000

Data Index: 336372 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.4141. Min Act: -0.0000

Data Index: 547543 (C4 (Web Text))

Max Activating Token Index: 831

Text #16

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.4006. Min Act: -0.0000

Data Index: 790403 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.3974. Min Act: -0.0000

Data Index: 276903 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.4069. Min Act: -0.0000

Data Index: 270787 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 0.5062. Min Range: -0.5062

Max Act: 0.4004. Min Act: -0.0000

Data Index: 747377 (C4 (Web Text))

Max Activating Token Index: 93