Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 186 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.7947. Min Act: -0.0001

Data Index: 372468 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.7552. Min Act: -0.0001

Data Index: 830684 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.7317. Min Act: -0.0002

Data Index: 697434 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.6989. Min Act: -0.0002

Data Index: 198529 (C4 (Web Text))

Max Activating Token Index: 564

Text #4

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.7419. Min Act: -0.0002

Data Index: 498575 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.7151. Min Act: -0.0001

Data Index: 483484 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.7073. Min Act: -0.0001

Data Index: 623516 (C4 (Web Text))

Max Activating Token Index: 520

Text #7

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.6828. Min Act: -0.0001

Data Index: 207063 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.6915. Min Act: -0.0002

Data Index: 18406 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.5738. Min Act: -0.0001

Data Index: 671294 (C4 (Web Text))

Max Activating Token Index: 739

Text #10

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.6904. Min Act: -0.0002

Data Index: 617141 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.6357. Min Act: -0.0001

Data Index: 1330660 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.6136. Min Act: -0.0002

Data Index: 806286 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.6753. Min Act: -0.0001

Data Index: 220870 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.6886. Min Act: -0.0002

Data Index: 143019 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.6043. Min Act: -0.0001

Data Index: 529041 (C4 (Web Text))

Max Activating Token Index: 603

Text #16

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.6922. Min Act: -0.0002

Data Index: 1068658 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.6914. Min Act: -0.0001

Data Index: 420764 (C4 (Web Text))

Max Activating Token Index: 323

Text #18

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.6596. Min Act: -0.0002

Data Index: 614154 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.6138. Min Act: -0.0002

Data Index: 758424 (C4 (Web Text))

Max Activating Token Index: 723