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

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

Neuron 3374 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: 0.7664. Min Range: -0.7664

Max Act: 0.7664. Min Act: -0.0001

Data Index: 913123 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 0.7664. Min Range: -0.7664

Max Act: 0.7574. Min Act: -0.0001

Data Index: 1230350 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 0.7664. Min Range: -0.7664

Max Act: 0.7151. Min Act: -0.0001

Data Index: 283286 (C4 (Web Text))

Max Activating Token Index: 952

Text #3

Max Range: 0.7664. Min Range: -0.7664

Max Act: 0.7068. Min Act: -0.0001

Data Index: 1352651 (C4 (Web Text))

Max Activating Token Index: 963

Text #4

Max Range: 0.7664. Min Range: -0.7664

Max Act: 0.7015. Min Act: -0.0001

Data Index: 355411 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 0.7664. Min Range: -0.7664

Max Act: 0.6524. Min Act: -0.0001

Data Index: 450310 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 0.7664. Min Range: -0.7664

Max Act: 0.6377. Min Act: -0.0001

Data Index: 1155356 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 0.7664. Min Range: -0.7664

Max Act: 0.6613. Min Act: -0.0001

Data Index: 207558 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 0.7664. Min Range: -0.7664

Max Act: 0.6329. Min Act: -0.0001

Data Index: 988201 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 0.7664. Min Range: -0.7664

Max Act: 0.6113. Min Act: -0.0001

Data Index: 1356008 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 0.7664. Min Range: -0.7664

Max Act: 0.6262. Min Act: -0.0001

Data Index: 158985 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 0.7664. Min Range: -0.7664

Max Act: 0.6236. Min Act: -0.0001

Data Index: 253779 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 0.7664. Min Range: -0.7664

Max Act: 0.6231. Min Act: -0.0001

Data Index: 1240882 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 0.7664. Min Range: -0.7664

Max Act: 0.6032. Min Act: -0.0001

Data Index: 744983 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 0.7664. Min Range: -0.7664

Max Act: 0.5999. Min Act: -0.0001

Data Index: 321043 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 0.7664. Min Range: -0.7664

Max Act: 0.6045. Min Act: -0.0001

Data Index: 495480 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 0.7664. Min Range: -0.7664

Max Act: 0.6197. Min Act: -0.0001

Data Index: 198709 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 0.7664. Min Range: -0.7664

Max Act: 0.6188. Min Act: -0.0001

Data Index: 692800 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 0.7664. Min Range: -0.7664

Max Act: 0.6140. Min Act: -0.0001

Data Index: 86818 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 0.7664. Min Range: -0.7664

Max Act: 0.5938. Min Act: -0.0001

Data Index: 1144013 (C4 (Web Text))

Max Activating Token Index: 501