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

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

Neuron 2118 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: 0.1093. Min Range: -0.1093

Max Act: 0.1093. Min Act: -0.0001

Data Index: 818229 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0978. Min Act: -0.0001

Data Index: 427147 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0967. Min Act: -0.0001

Data Index: 1039008 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0903. Min Act: -0.0001

Data Index: 1046550 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0922. Min Act: -0.0000

Data Index: 1212093 (C4 (Web Text))

Max Activating Token Index: 534

Text #5

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.1035. Min Act: -0.0001

Data Index: 732927 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0957. Min Act: -0.0001

Data Index: 83431 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0854. Min Act: -0.0001

Data Index: 1251857 (C4 (Web Text))

Max Activating Token Index: 561

Text #8

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0924. Min Act: -0.0001

Data Index: 1187766 (C4 (Web Text))

Max Activating Token Index: 133

Text #9

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0924. Min Act: -0.0001

Data Index: 693096 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0979. Min Act: -0.0001

Data Index: 348743 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0890. Min Act: -0.0001

Data Index: 992988 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0902. Min Act: -0.0001

Data Index: 360957 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0869. Min Act: -0.0001

Data Index: 1290077 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0832. Min Act: -0.0001

Data Index: 739882 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0830. Min Act: -0.0001

Data Index: 835491 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0846. Min Act: -0.0001

Data Index: 296479 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0872. Min Act: -0.0001

Data Index: 9341 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0852. Min Act: -0.0001

Data Index: 1113113 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0843. Min Act: -0.0001

Data Index: 701139 (C4 (Web Text))

Max Activating Token Index: 903