Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1885 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6985. Min Act: -0.0001

Data Index: 131736 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6138. Min Act: -0.0001

Data Index: 657521 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6379. Min Act: -0.0001

Data Index: 108866 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6005. Min Act: -0.0001

Data Index: 172353 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.5277. Min Act: -0.0001

Data Index: 785629 (C4 (Web Text))

Max Activating Token Index: 722

Text #5

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.5509. Min Act: -0.0001

Data Index: 992346 (C4 (Web Text))

Max Activating Token Index: 290

Text #6

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.5412. Min Act: -0.0001

Data Index: 60421 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.4883. Min Act: -0.0001

Data Index: 1285282 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.5188. Min Act: -0.0001

Data Index: 995350 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.4738. Min Act: -0.0001

Data Index: 898254 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.4646. Min Act: -0.0001

Data Index: 508377 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.5009. Min Act: -0.0001

Data Index: 994741 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.4497. Min Act: -0.0001

Data Index: 225826 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.4512. Min Act: -0.0001

Data Index: 533088 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.4380. Min Act: -0.0001

Data Index: 1039521 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.4412. Min Act: -0.0001

Data Index: 635349 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.4243. Min Act: -0.0001

Data Index: 906074 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.4248. Min Act: -0.0001

Data Index: 819185 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.4234. Min Act: -0.0001

Data Index: 681515 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.4779. Min Act: -0.0001

Data Index: 1215875 (C4 (Web Text))

Max Activating Token Index: 234