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

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

Neuron 1847 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.6940. Min Act: -0.0001

Data Index: 1608424 (Python Code)

Max Activating Token Index: 477

Text #1

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.6061. Min Act: -0.0000

Data Index: 1101909 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.6230. Min Act: -0.0000

Data Index: 764831 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5770. Min Act: -0.0001

Data Index: 565781 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5232. Min Act: -0.0001

Data Index: 1276551 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5452. Min Act: -0.0001

Data Index: 1349859 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5127. Min Act: -0.0000

Data Index: 1296244 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.4850. Min Act: -0.0000

Data Index: 2620 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.5645. Min Act: -0.0001

Data Index: 989722 (C4 (Web Text))

Max Activating Token Index: 977

Text #9

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.4468. Min Act: -0.0000

Data Index: 744091 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.4546. Min Act: -0.0001

Data Index: 131121 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.4948. Min Act: -0.0000

Data Index: 685591 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.4617. Min Act: -0.0000

Data Index: 80411 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.4477. Min Act: -0.0000

Data Index: 1343952 (C4 (Web Text))

Max Activating Token Index: 519

Text #14

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.4782. Min Act: -0.0000

Data Index: 1163035 (C4 (Web Text))

Max Activating Token Index: 622

Text #15

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.4147. Min Act: -0.0001

Data Index: 124560 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.4670. Min Act: -0.0001

Data Index: 931456 (C4 (Web Text))

Max Activating Token Index: 598

Text #17

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.4268. Min Act: -0.0000

Data Index: 1284333 (C4 (Web Text))

Max Activating Token Index: 556

Text #18

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.3780. Min Act: -0.0000

Data Index: 1281834 (C4 (Web Text))

Max Activating Token Index: 333

Text #19

Max Range: 0.6940. Min Range: -0.6940

Max Act: 0.4150. Min Act: -0.0000

Data Index: 880817 (C4 (Web Text))

Max Activating Token Index: 804