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

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

Neuron 2726 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: 1.2957. Min Range: -1.2957

Max Act: 1.2005. Min Act: -0.0001

Data Index: 705094 (C4 (Web Text))

Max Activating Token Index: 641

Text #1

Max Range: 1.2957. Min Range: -1.2957

Max Act: 1.2397. Min Act: -0.0002

Data Index: 575181 (C4 (Web Text))

Max Activating Token Index: 599

Text #2

Max Range: 1.2957. Min Range: -1.2957

Max Act: 1.1902. Min Act: -0.0001

Data Index: 1090153 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 1.2957. Min Range: -1.2957

Max Act: 1.0543. Min Act: -0.0001

Data Index: 649520 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 1.2957. Min Range: -1.2957

Max Act: 1.0339. Min Act: -0.0001

Data Index: 307196 (C4 (Web Text))

Max Activating Token Index: 649

Text #5

Max Range: 1.2957. Min Range: -1.2957

Max Act: 1.0720. Min Act: -0.0001

Data Index: 139362 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 1.2957. Min Range: -1.2957

Max Act: 1.2052. Min Act: -0.0002

Data Index: 537971 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 1.2957. Min Range: -1.2957

Max Act: 1.1681. Min Act: -0.0001

Data Index: 434696 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 1.2957. Min Range: -1.2957

Max Act: 1.0885. Min Act: -0.0002

Data Index: 556445 (C4 (Web Text))

Max Activating Token Index: 402

Text #9

Max Range: 1.2957. Min Range: -1.2957

Max Act: 1.1478. Min Act: -0.0002

Data Index: 647597 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 1.2957. Min Range: -1.2957

Max Act: 1.2957. Min Act: -0.0001

Data Index: 777729 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 1.2957. Min Range: -1.2957

Max Act: 1.1821. Min Act: -0.0002

Data Index: 236546 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 1.2957. Min Range: -1.2957

Max Act: 1.0623. Min Act: -0.0002

Data Index: 220557 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 1.2957. Min Range: -1.2957

Max Act: 1.2919. Min Act: -0.0001

Data Index: 1042917 (C4 (Web Text))

Max Activating Token Index: 676

Text #14

Max Range: 1.2957. Min Range: -1.2957

Max Act: 1.2132. Min Act: -0.0002

Data Index: 742792 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 1.2957. Min Range: -1.2957

Max Act: 1.2230. Min Act: -0.0001

Data Index: 886896 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 1.2957. Min Range: -1.2957

Max Act: 1.0898. Min Act: -0.0002

Data Index: 1085877 (C4 (Web Text))

Max Activating Token Index: 804

Text #17

Max Range: 1.2957. Min Range: -1.2957

Max Act: 1.0825. Min Act: -0.0001

Data Index: 109691 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 1.2957. Min Range: -1.2957

Max Act: 1.0469. Min Act: -0.0001

Data Index: 1339688 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 1.2957. Min Range: -1.2957

Max Act: 1.0262. Min Act: -0.0002

Data Index: 522617 (C4 (Web Text))

Max Activating Token Index: 608