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

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

Neuron 1371 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: 0.1176. Min Range: -0.1176

Max Act: 0.1176. Min Act: -0.0001

Data Index: 113904 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1176. Min Act: -0.0001

Data Index: 1258707 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1102. Min Act: -0.0001

Data Index: 930613 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1050. Min Act: -0.0001

Data Index: 785514 (C4 (Web Text))

Max Activating Token Index: 621

Text #4

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1024. Min Act: -0.0001

Data Index: 1182114 (C4 (Web Text))

Max Activating Token Index: 981

Text #5

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1015. Min Act: -0.0001

Data Index: 863924 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0973. Min Act: -0.0001

Data Index: 706619 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0953. Min Act: -0.0001

Data Index: 1005242 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1014. Min Act: -0.0001

Data Index: 1022485 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0906. Min Act: -0.0001

Data Index: 443544 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1085. Min Act: -0.0001

Data Index: 1341047 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0898. Min Act: -0.0001

Data Index: 504620 (C4 (Web Text))

Max Activating Token Index: 457

Text #12

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0946. Min Act: -0.0001

Data Index: 705192 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0940. Min Act: -0.0001

Data Index: 716160 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0910. Min Act: -0.0001

Data Index: 1048818 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0901. Min Act: -0.0001

Data Index: 1081757 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0867. Min Act: -0.0002

Data Index: 27387 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0858. Min Act: -0.0001

Data Index: 815855 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0894. Min Act: -0.0001

Data Index: 605684 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.0961. Min Act: -0.0001

Data Index: 1322495 (C4 (Web Text))

Max Activating Token Index: 809