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

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

Neuron 658 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1593. Min Range: -1.1593

Max Act: 1.1593. Min Act: -0.0003

Data Index: 258083 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 1.1593. Min Range: -1.1593

Max Act: 1.1534. Min Act: -0.0003

Data Index: 789100 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 1.1593. Min Range: -1.1593

Max Act: 1.0238. Min Act: -0.0003

Data Index: 243284 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 1.1593. Min Range: -1.1593

Max Act: 1.0740. Min Act: -0.0003

Data Index: 967904 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 1.1593. Min Range: -1.1593

Max Act: 1.0206. Min Act: -0.0003

Data Index: 139959 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.9268. Min Act: -0.0003

Data Index: 1039934 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.8511. Min Act: -0.0003

Data Index: 291605 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.8963. Min Act: -0.0003

Data Index: 572310 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.9175. Min Act: -0.0003

Data Index: 1094756 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.8830. Min Act: -0.0003

Data Index: 1202514 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.8759. Min Act: -0.0003

Data Index: 709166 (C4 (Web Text))

Max Activating Token Index: 878

Text #11

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.7774. Min Act: -0.0003

Data Index: 995888 (C4 (Web Text))

Max Activating Token Index: 452

Text #12

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.8393. Min Act: -0.0004

Data Index: 1037788 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.8384. Min Act: -0.0003

Data Index: 1162088 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.8349. Min Act: -0.0003

Data Index: 1257277 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.8336. Min Act: -0.0003

Data Index: 1124246 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.8593. Min Act: -0.0003

Data Index: 11059 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.7972. Min Act: -0.0003

Data Index: 798759 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.8047. Min Act: -0.0003

Data Index: 986751 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.8499. Min Act: -0.0003

Data Index: 1058274 (C4 (Web Text))

Max Activating Token Index: 1023