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

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

Neuron 3679 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: 0.3683. Min Range: -0.3683

Max Act: 0.3683. Min Act: -0.0000

Data Index: 194189 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.3178. Min Act: -0.0000

Data Index: 615189 (C4 (Web Text))

Max Activating Token Index: 931

Text #2

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.3047. Min Act: -0.0000

Data Index: 943156 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2748. Min Act: -0.0000

Data Index: 1239437 (C4 (Web Text))

Max Activating Token Index: 291

Text #4

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2656. Min Act: -0.0000

Data Index: 1322187 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2530. Min Act: -0.0000

Data Index: 795900 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2525. Min Act: -0.0000

Data Index: 1027671 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2291. Min Act: -0.0000

Data Index: 990442 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2367. Min Act: -0.0000

Data Index: 1054822 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2215. Min Act: -0.0000

Data Index: 933483 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2162. Min Act: -0.0000

Data Index: 743937 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2245. Min Act: -0.0000

Data Index: 608887 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2218. Min Act: -0.0000

Data Index: 1022499 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2136. Min Act: -0.0000

Data Index: 77448 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2109. Min Act: -0.0000

Data Index: 824981 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2153. Min Act: -0.0000

Data Index: 1027088 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2316. Min Act: -0.0000

Data Index: 328063 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.1777. Min Act: -0.0000

Data Index: 1268359 (C4 (Web Text))

Max Activating Token Index: 681

Text #18

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2057. Min Act: -0.0000

Data Index: 765565 (C4 (Web Text))

Max Activating Token Index: 656

Text #19

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2199. Min Act: -0.0000

Data Index: 330977 (C4 (Web Text))

Max Activating Token Index: 183