Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3330 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.7191. Min Act: -0.0001

Data Index: 1029296 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.8306. Min Act: -0.0001

Data Index: 92220 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.8599. Min Act: -0.0000

Data Index: 405766 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.6560. Min Act: -0.0000

Data Index: 281929 (C4 (Web Text))

Max Activating Token Index: 839

Text #4

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.5665. Min Act: -0.0001

Data Index: 260895 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.6926. Min Act: -0.0000

Data Index: 420548 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.4137. Min Act: -0.0000

Data Index: 131646 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.8379. Min Act: -0.0000

Data Index: 1151411 (C4 (Web Text))

Max Activating Token Index: 677

Text #8

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.4355. Min Act: -0.0001

Data Index: 757731 (C4 (Web Text))

Max Activating Token Index: 828

Text #9

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.3053. Min Act: -0.0001

Data Index: 428818 (C4 (Web Text))

Max Activating Token Index: 699

Text #10

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.4019. Min Act: -0.0001

Data Index: 228070 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.3081. Min Act: -0.0001

Data Index: 594769 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.6153. Min Act: -0.0001

Data Index: 1088931 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.3604. Min Act: -0.0000

Data Index: 749807 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.3241. Min Act: -0.0001

Data Index: 923961 (C4 (Web Text))

Max Activating Token Index: 737

Text #15

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.5543. Min Act: -0.0001

Data Index: 781575 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.3904. Min Act: -0.0000

Data Index: 1057957 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.2810. Min Act: -0.0000

Data Index: 815055 (C4 (Web Text))

Max Activating Token Index: 416

Text #18

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.3126. Min Act: -0.0000

Data Index: 1315680 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.3586. Min Act: -0.0000

Data Index: 714181 (C4 (Web Text))

Max Activating Token Index: 438