Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4753 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.7141. Min Act: -0.0000

Data Index: 664515 (C4 (Web Text))

Max Activating Token Index: 843

Text #1

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.6838. Min Act: -0.0000

Data Index: 1248413 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.6222. Min Act: -0.0000

Data Index: 1263684 (C4 (Web Text))

Max Activating Token Index: 888

Text #3

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.5793. Min Act: -0.0000

Data Index: 424876 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.5914. Min Act: -0.0000

Data Index: 1120866 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.5701. Min Act: -0.0000

Data Index: 207671 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.6181. Min Act: -0.0000

Data Index: 463646 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.5594. Min Act: -0.0000

Data Index: 1357878 (C4 (Web Text))

Max Activating Token Index: 440

Text #8

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.5410. Min Act: -0.0000

Data Index: 856274 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.5361. Min Act: -0.0000

Data Index: 822837 (C4 (Web Text))

Max Activating Token Index: 983

Text #10

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.5790. Min Act: -0.0000

Data Index: 759040 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.5256. Min Act: -0.0000

Data Index: 904762 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.5395. Min Act: -0.0000

Data Index: 1120981 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.5065. Min Act: -0.0000

Data Index: 145462 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.5183. Min Act: -0.0000

Data Index: 1132936 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.4970. Min Act: -0.0000

Data Index: 454863 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.5109. Min Act: -0.0000

Data Index: 841441 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.4874. Min Act: -0.0000

Data Index: 1316761 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.4594. Min Act: -0.0000

Data Index: 1031019 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 0.7141. Min Range: -0.7141

Max Act: 0.4890. Min Act: -0.0000

Data Index: 885130 (C4 (Web Text))

Max Activating Token Index: 325