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

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

Neuron 1776 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1798. Min Act: -0.0001

Data Index: 1017444 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1438. Min Act: -0.0001

Data Index: 1357341 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1360. Min Act: -0.0001

Data Index: 783444 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1271. Min Act: -0.0001

Data Index: 1348100 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1111. Min Act: -0.0001

Data Index: 559175 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1102. Min Act: -0.0001

Data Index: 264109 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1109. Min Act: -0.0001

Data Index: 1048965 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1080. Min Act: -0.0001

Data Index: 89949 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1084. Min Act: -0.0001

Data Index: 1003997 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1022. Min Act: -0.0001

Data Index: 998522 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.0981. Min Act: -0.0001

Data Index: 1150606 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1000. Min Act: -0.0001

Data Index: 1029125 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1076. Min Act: -0.0001

Data Index: 908572 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.0904. Min Act: -0.0001

Data Index: 1149913 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1001. Min Act: -0.0001

Data Index: 97618 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.0934. Min Act: -0.0001

Data Index: 911937 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.0892. Min Act: -0.0001

Data Index: 789885 (C4 (Web Text))

Max Activating Token Index: 578

Text #17

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.0953. Min Act: -0.0001

Data Index: 169248 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.0961. Min Act: -0.0001

Data Index: 1033747 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.0946. Min Act: -0.0001

Data Index: 584467 (C4 (Web Text))

Max Activating Token Index: 579