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

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

Neuron 243 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5066. Min Range: -2.5066

Max Act: 2.5066. Min Act: -0.0000

Data Index: 1170340 (C4 (Web Text))

Max Activating Token Index: 513

Text #1

Max Range: 2.5066. Min Range: -2.5066

Max Act: 2.4251. Min Act: -0.0000

Data Index: 108778 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 2.5066. Min Range: -2.5066

Max Act: 2.4736. Min Act: -0.0000

Data Index: 390343 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 2.5066. Min Range: -2.5066

Max Act: 2.3145. Min Act: -0.0000

Data Index: 320537 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 2.5066. Min Range: -2.5066

Max Act: 2.2832. Min Act: -0.0000

Data Index: 1330822 (C4 (Web Text))

Max Activating Token Index: 535

Text #5

Max Range: 2.5066. Min Range: -2.5066

Max Act: 2.2679. Min Act: -0.0000

Data Index: 334921 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 2.5066. Min Range: -2.5066

Max Act: 2.0473. Min Act: -0.0000

Data Index: 1004238 (C4 (Web Text))

Max Activating Token Index: 690

Text #7

Max Range: 2.5066. Min Range: -2.5066

Max Act: 2.0780. Min Act: -0.0000

Data Index: 641942 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 2.5066. Min Range: -2.5066

Max Act: 2.0516. Min Act: -0.0000

Data Index: 1244260 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 2.5066. Min Range: -2.5066

Max Act: 2.1052. Min Act: -0.0000

Data Index: 564445 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 2.5066. Min Range: -2.5066

Max Act: 1.9863. Min Act: -0.0000

Data Index: 119077 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 2.5066. Min Range: -2.5066

Max Act: 1.8591. Min Act: -0.0000

Data Index: 1129759 (C4 (Web Text))

Max Activating Token Index: 468

Text #12

Max Range: 2.5066. Min Range: -2.5066

Max Act: 1.9218. Min Act: -0.0000

Data Index: 447217 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 2.5066. Min Range: -2.5066

Max Act: 1.8377. Min Act: -0.0000

Data Index: 908357 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 2.5066. Min Range: -2.5066

Max Act: 1.8647. Min Act: -0.0000

Data Index: 16747 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 2.5066. Min Range: -2.5066

Max Act: 1.9768. Min Act: -0.0000

Data Index: 179008 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 2.5066. Min Range: -2.5066

Max Act: 1.7429. Min Act: -0.0000

Data Index: 268588 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 2.5066. Min Range: -2.5066

Max Act: 1.9672. Min Act: -0.0000

Data Index: 407820 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 2.5066. Min Range: -2.5066

Max Act: 1.8201. Min Act: -0.0000

Data Index: 219372 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 2.5066. Min Range: -2.5066

Max Act: 1.6889. Min Act: -0.0000

Data Index: 1188837 (C4 (Web Text))

Max Activating Token Index: 49