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

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

Neuron 4055 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.5438. Min Act: -0.0000

Data Index: 210185 (C4 (Web Text))

Max Activating Token Index: 1010

Text #1

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.5340. Min Act: -0.0000

Data Index: 1115837 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4718. Min Act: -0.0000

Data Index: 364747 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.5181. Min Act: -0.0000

Data Index: 817988 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.5037. Min Act: -0.0000

Data Index: 496852 (C4 (Web Text))

Max Activating Token Index: 584

Text #5

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.5352. Min Act: -0.0000

Data Index: 805124 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.5294. Min Act: -0.0000

Data Index: 828642 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4842. Min Act: -0.0000

Data Index: 946658 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4543. Min Act: -0.0000

Data Index: 420452 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4199. Min Act: -0.0000

Data Index: 1214369 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4264. Min Act: -0.0000

Data Index: 777365 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4147. Min Act: -0.0000

Data Index: 1203817 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4322. Min Act: -0.0000

Data Index: 1237576 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4183. Min Act: -0.0000

Data Index: 492790 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4023. Min Act: -0.0000

Data Index: 440644 (C4 (Web Text))

Max Activating Token Index: 521

Text #15

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4357. Min Act: -0.0000

Data Index: 1282089 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4399. Min Act: -0.0000

Data Index: 194014 (C4 (Web Text))

Max Activating Token Index: 472

Text #17

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4341. Min Act: -0.0000

Data Index: 351864 (C4 (Web Text))

Max Activating Token Index: 995

Text #18

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4086. Min Act: -0.0000

Data Index: 1037636 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.3785. Min Act: -0.0000

Data Index: 823878 (C4 (Web Text))

Max Activating Token Index: 180