Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1340 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.5707. Min Range: -4.5707

Max Act: 4.5150. Min Act: -0.0000

Data Index: 1091780 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 4.5707. Min Range: -4.5707

Max Act: 4.5707. Min Act: -0.0000

Data Index: 1116166 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 4.5707. Min Range: -4.5707

Max Act: 4.1729. Min Act: -0.0000

Data Index: 849476 (C4 (Web Text))

Max Activating Token Index: 160

Text #3

Max Range: 4.5707. Min Range: -4.5707

Max Act: 3.9658. Min Act: -0.0000

Data Index: 14665 (C4 (Web Text))

Max Activating Token Index: 526

Text #4

Max Range: 4.5707. Min Range: -4.5707

Max Act: 3.3042. Min Act: -0.0000

Data Index: 1198127 (C4 (Web Text))

Max Activating Token Index: 869

Text #5

Max Range: 4.5707. Min Range: -4.5707

Max Act: 3.1603. Min Act: -0.0000

Data Index: 1005962 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 4.5707. Min Range: -4.5707

Max Act: 3.4458. Min Act: -0.0000

Data Index: 217434 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 4.5707. Min Range: -4.5707

Max Act: 3.2085. Min Act: -0.0000

Data Index: 1246564 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 4.5707. Min Range: -4.5707

Max Act: 3.0229. Min Act: -0.0000

Data Index: 698836 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 4.5707. Min Range: -4.5707

Max Act: 3.1471. Min Act: -0.0000

Data Index: 230945 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 4.5707. Min Range: -4.5707

Max Act: 3.1535. Min Act: -0.0000

Data Index: 1075024 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 4.5707. Min Range: -4.5707

Max Act: 2.9764. Min Act: -0.0000

Data Index: 766452 (C4 (Web Text))

Max Activating Token Index: 623

Text #12

Max Range: 4.5707. Min Range: -4.5707

Max Act: 3.1346. Min Act: -0.0000

Data Index: 1166202 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 4.5707. Min Range: -4.5707

Max Act: 2.8006. Min Act: -0.0000

Data Index: 1354787 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 4.5707. Min Range: -4.5707

Max Act: 2.9393. Min Act: -0.0000

Data Index: 1203711 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 4.5707. Min Range: -4.5707

Max Act: 3.0833. Min Act: -0.0000

Data Index: 1190829 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 4.5707. Min Range: -4.5707

Max Act: 2.9398. Min Act: -0.0000

Data Index: 141023 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 4.5707. Min Range: -4.5707

Max Act: 3.0606. Min Act: -0.0000

Data Index: 116140 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 4.5707. Min Range: -4.5707

Max Act: 2.9093. Min Act: -0.0000

Data Index: 1101499 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 4.5707. Min Range: -4.5707

Max Act: 2.7615. Min Act: -0.0000

Data Index: 160362 (C4 (Web Text))

Max Activating Token Index: 520