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

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

Neuron 2456 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1170. Min Act: -0.0002

Data Index: 1174669 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1059. Min Act: -0.0002

Data Index: 96212 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0915. Min Act: -0.0002

Data Index: 1127046 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0950. Min Act: -0.0002

Data Index: 876581 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0948. Min Act: -0.0002

Data Index: 492535 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0907. Min Act: -0.0002

Data Index: 167238 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0999. Min Act: -0.0002

Data Index: 644660 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0940. Min Act: -0.0002

Data Index: 126547 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0965. Min Act: -0.0002

Data Index: 275184 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0879. Min Act: -0.0002

Data Index: 847054 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0903. Min Act: -0.0002

Data Index: 631740 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0934. Min Act: -0.0002

Data Index: 147501 (C4 (Web Text))

Max Activating Token Index: 455

Text #12

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0731. Min Act: -0.0002

Data Index: 1071121 (C4 (Web Text))

Max Activating Token Index: 823

Text #13

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0839. Min Act: -0.0002

Data Index: 254567 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0867. Min Act: -0.0002

Data Index: 1295597 (C4 (Web Text))

Max Activating Token Index: 596

Text #15

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0781. Min Act: -0.0002

Data Index: 17251 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0878. Min Act: -0.0002

Data Index: 515814 (C4 (Web Text))

Max Activating Token Index: 216

Text #17

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0859. Min Act: -0.0002

Data Index: 1172884 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0915. Min Act: -0.0002

Data Index: 1337097 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0825. Min Act: -0.0002

Data Index: 591492 (C4 (Web Text))

Max Activating Token Index: 123