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

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

Neuron 3780 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7587. Min Range: -1.7587

Max Act: 1.7587. Min Act: -0.0000

Data Index: 567342 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 1.7587. Min Range: -1.7587

Max Act: 1.5144. Min Act: -0.0000

Data Index: 16530 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 1.7587. Min Range: -1.7587

Max Act: 1.4093. Min Act: -0.0000

Data Index: 341907 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 1.7587. Min Range: -1.7587

Max Act: 1.3212. Min Act: -0.0000

Data Index: 498105 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 1.7587. Min Range: -1.7587

Max Act: 1.2014. Min Act: -0.0000

Data Index: 450009 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 1.7587. Min Range: -1.7587

Max Act: 1.2282. Min Act: -0.0000

Data Index: 522669 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 1.7587. Min Range: -1.7587

Max Act: 1.1529. Min Act: -0.0000

Data Index: 745239 (C4 (Web Text))

Max Activating Token Index: 797

Text #7

Max Range: 1.7587. Min Range: -1.7587

Max Act: 1.1534. Min Act: -0.0000

Data Index: 975514 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 1.7587. Min Range: -1.7587

Max Act: 1.0944. Min Act: -0.0000

Data Index: 68274 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 1.7587. Min Range: -1.7587

Max Act: 1.1620. Min Act: -0.0000

Data Index: 358513 (C4 (Web Text))

Max Activating Token Index: 443

Text #10

Max Range: 1.7587. Min Range: -1.7587

Max Act: 1.1012. Min Act: -0.0000

Data Index: 580069 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 1.7587. Min Range: -1.7587

Max Act: 1.0932. Min Act: -0.0000

Data Index: 842755 (C4 (Web Text))

Max Activating Token Index: 202

Text #12

Max Range: 1.7587. Min Range: -1.7587

Max Act: 1.0830. Min Act: -0.0000

Data Index: 770272 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 1.7587. Min Range: -1.7587

Max Act: 1.0558. Min Act: -0.0000

Data Index: 978477 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 1.7587. Min Range: -1.7587

Max Act: 1.0583. Min Act: -0.0000

Data Index: 550170 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 1.7587. Min Range: -1.7587

Max Act: 1.0418. Min Act: -0.0000

Data Index: 783559 (C4 (Web Text))

Max Activating Token Index: 965

Text #16

Max Range: 1.7587. Min Range: -1.7587

Max Act: 1.0393. Min Act: -0.0000

Data Index: 1178843 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 1.7587. Min Range: -1.7587

Max Act: 1.0958. Min Act: -0.0000

Data Index: 377015 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 1.7587. Min Range: -1.7587

Max Act: 1.0194. Min Act: -0.0000

Data Index: 1336981 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 1.7587. Min Range: -1.7587

Max Act: 1.0072. Min Act: -0.0000

Data Index: 75868 (C4 (Web Text))

Max Activating Token Index: 162