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

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

Neuron 2282 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.6472. Min Act: -0.0001

Data Index: 1301495 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.6059. Min Act: -0.0001

Data Index: 290241 (C4 (Web Text))

Max Activating Token Index: 769

Text #2

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.6155. Min Act: -0.0001

Data Index: 742597 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.6042. Min Act: -0.0001

Data Index: 783265 (C4 (Web Text))

Max Activating Token Index: 293

Text #4

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5623. Min Act: -0.0001

Data Index: 1208178 (C4 (Web Text))

Max Activating Token Index: 67

Text #5

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5836. Min Act: -0.0001

Data Index: 926988 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5694. Min Act: -0.0001

Data Index: 716795 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5161. Min Act: -0.0001

Data Index: 528620 (C4 (Web Text))

Max Activating Token Index: 719

Text #8

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5458. Min Act: -0.0001

Data Index: 1134537 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5423. Min Act: -0.0001

Data Index: 1301943 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5871. Min Act: -0.0001

Data Index: 888899 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5564. Min Act: -0.0001

Data Index: 3688 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5440. Min Act: -0.0001

Data Index: 968300 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5416. Min Act: -0.0001

Data Index: 184315 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5033. Min Act: -0.0001

Data Index: 990948 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.4762. Min Act: -0.0001

Data Index: 402745 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5258. Min Act: -0.0001

Data Index: 114971 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.4866. Min Act: -0.0001

Data Index: 410022 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5327. Min Act: -0.0001

Data Index: 1018683 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.4644. Min Act: -0.0001

Data Index: 345870 (C4 (Web Text))

Max Activating Token Index: 647