Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3799 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.5052. Min Act: -0.0000

Data Index: 549797 (C4 (Web Text))

Max Activating Token Index: 431

Text #1

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.1105. Min Act: -0.0000

Data Index: 307760 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.1724. Min Act: -0.0000

Data Index: 324704 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.2103. Min Act: 0.0000

Data Index: 255863 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.1472. Min Act: -0.0000

Data Index: 1358210 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.0263. Min Act: -0.0000

Data Index: 746413 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.0422. Min Act: -0.0000

Data Index: 587019 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 1.5052. Min Range: -1.5052

Max Act: 0.9782. Min Act: -0.0000

Data Index: 852619 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 1.5052. Min Range: -1.5052

Max Act: 0.9729. Min Act: -0.0000

Data Index: 9443 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 1.5052. Min Range: -1.5052

Max Act: 0.8635. Min Act: -0.0000

Data Index: 667405 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 1.5052. Min Range: -1.5052

Max Act: 0.9561. Min Act: -0.0000

Data Index: 809977 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.0922. Min Act: -0.0000

Data Index: 791152 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.0214. Min Act: -0.0000

Data Index: 748633 (C4 (Web Text))

Max Activating Token Index: 884

Text #13

Max Range: 1.5052. Min Range: -1.5052

Max Act: 1.0168. Min Act: -0.0000

Data Index: 574840 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 1.5052. Min Range: -1.5052

Max Act: 0.9549. Min Act: -0.0000

Data Index: 881428 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 1.5052. Min Range: -1.5052

Max Act: 0.9439. Min Act: -0.0000

Data Index: 1301671 (C4 (Web Text))

Max Activating Token Index: 490

Text #16

Max Range: 1.5052. Min Range: -1.5052

Max Act: 0.9210. Min Act: -0.0000

Data Index: 247994 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 1.5052. Min Range: -1.5052

Max Act: 0.8957. Min Act: -0.0000

Data Index: 843600 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 1.5052. Min Range: -1.5052

Max Act: 0.9966. Min Act: -0.0000

Data Index: 1141975 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 1.5052. Min Range: -1.5052

Max Act: 0.9007. Min Act: 0.0000

Data Index: 905011 (C4 (Web Text))

Max Activating Token Index: 56