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

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

Neuron 3373 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: 0.5073. Min Range: -0.5073

Max Act: 0.5073. Min Act: -0.0003

Data Index: 899906 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.4441. Min Act: -0.0003

Data Index: 179716 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.4257. Min Act: -0.0003

Data Index: 535567 (C4 (Web Text))

Max Activating Token Index: 952

Text #3

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.4295. Min Act: -0.0003

Data Index: 1052402 (C4 (Web Text))

Max Activating Token Index: 809

Text #4

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.4046. Min Act: -0.0003

Data Index: 381857 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.4269. Min Act: -0.0003

Data Index: 892557 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.4135. Min Act: -0.0003

Data Index: 730301 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.4203. Min Act: -0.0003

Data Index: 98070 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.4197. Min Act: -0.0003

Data Index: 671431 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.4205. Min Act: -0.0003

Data Index: 933481 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.4313. Min Act: -0.0003

Data Index: 756693 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.4334. Min Act: -0.0003

Data Index: 794260 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.4022. Min Act: -0.0003

Data Index: 186970 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.4046. Min Act: -0.0003

Data Index: 508659 (C4 (Web Text))

Max Activating Token Index: 762

Text #14

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.4166. Min Act: -0.0003

Data Index: 409083 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.3912. Min Act: -0.0003

Data Index: 752363 (C4 (Web Text))

Max Activating Token Index: 418

Text #16

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.4014. Min Act: -0.0003

Data Index: 692571 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.4150. Min Act: -0.0003

Data Index: 393102 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.4263. Min Act: -0.0003

Data Index: 127154 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.4016. Min Act: -0.0003

Data Index: 880265 (C4 (Web Text))

Max Activating Token Index: 732