Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4081 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1147. Min Act: -0.0000

Data Index: 460790 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1118. Min Act: -0.0000

Data Index: 1324110 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1125. Min Act: -0.0000

Data Index: 315001 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1039. Min Act: -0.0000

Data Index: 692537 (C4 (Web Text))

Max Activating Token Index: 198

Text #4

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1010. Min Act: -0.0000

Data Index: 860330 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1036. Min Act: -0.0000

Data Index: 840334 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1022. Min Act: -0.0000

Data Index: 971998 (C4 (Web Text))

Max Activating Token Index: 668

Text #7

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1017. Min Act: -0.0000

Data Index: 651502 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1047. Min Act: -0.0000

Data Index: 160025 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1006. Min Act: -0.0000

Data Index: 215166 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0970. Min Act: -0.0000

Data Index: 132931 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1008. Min Act: 0.0001

Data Index: 671249 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1035. Min Act: -0.0000

Data Index: 1354842 (C4 (Web Text))

Max Activating Token Index: 949

Text #13

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0928. Min Act: -0.0000

Data Index: 212079 (C4 (Web Text))

Max Activating Token Index: 969

Text #14

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0924. Min Act: -0.0000

Data Index: 1132531 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0936. Min Act: -0.0000

Data Index: 177432 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0965. Min Act: -0.0000

Data Index: 270316 (C4 (Web Text))

Max Activating Token Index: 985

Text #17

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0940. Min Act: -0.0000

Data Index: 1353052 (C4 (Web Text))

Max Activating Token Index: 438

Text #18

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0899. Min Act: -0.0000

Data Index: 434606 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0925. Min Act: -0.0000

Data Index: 1195498 (C4 (Web Text))

Max Activating Token Index: 416