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

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

Neuron 2363 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5563. Min Range: -0.5563

Max Act: 0.5563. Min Act: -0.0001

Data Index: 1009998 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 0.5563. Min Range: -0.5563

Max Act: 0.5509. Min Act: -0.0001

Data Index: 1261622 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 0.5563. Min Range: -0.5563

Max Act: 0.5390. Min Act: -0.0001

Data Index: 11563 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 0.5563. Min Range: -0.5563

Max Act: 0.5126. Min Act: -0.0001

Data Index: 879914 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 0.5563. Min Range: -0.5563

Max Act: 0.5053. Min Act: -0.0001

Data Index: 1257801 (C4 (Web Text))

Max Activating Token Index: 352

Text #5

Max Range: 0.5563. Min Range: -0.5563

Max Act: 0.5489. Min Act: -0.0001

Data Index: 1111016 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 0.5563. Min Range: -0.5563

Max Act: 0.4816. Min Act: -0.0001

Data Index: 1351253 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 0.5563. Min Range: -0.5563

Max Act: 0.4921. Min Act: -0.0001

Data Index: 15757 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 0.5563. Min Range: -0.5563

Max Act: 0.4883. Min Act: -0.0001

Data Index: 102667 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 0.5563. Min Range: -0.5563

Max Act: 0.4955. Min Act: -0.0001

Data Index: 450231 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 0.5563. Min Range: -0.5563

Max Act: 0.4984. Min Act: -0.0001

Data Index: 432397 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 0.5563. Min Range: -0.5563

Max Act: 0.5091. Min Act: -0.0001

Data Index: 1035826 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 0.5563. Min Range: -0.5563

Max Act: 0.4457. Min Act: -0.0001

Data Index: 322557 (C4 (Web Text))

Max Activating Token Index: 698

Text #13

Max Range: 0.5563. Min Range: -0.5563

Max Act: 0.4558. Min Act: -0.0001

Data Index: 909494 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 0.5563. Min Range: -0.5563

Max Act: 0.4543. Min Act: -0.0001

Data Index: 578668 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 0.5563. Min Range: -0.5563

Max Act: 0.4330. Min Act: -0.0001

Data Index: 1269513 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 0.5563. Min Range: -0.5563

Max Act: 0.4272. Min Act: -0.0001

Data Index: 261854 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 0.5563. Min Range: -0.5563

Max Act: 0.4563. Min Act: -0.0001

Data Index: 322874 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 0.5563. Min Range: -0.5563

Max Act: 0.4479. Min Act: -0.0001

Data Index: 615087 (C4 (Web Text))

Max Activating Token Index: 559

Text #19

Max Range: 0.5563. Min Range: -0.5563

Max Act: 0.4210. Min Act: -0.0001

Data Index: 1260096 (C4 (Web Text))

Max Activating Token Index: 200