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

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

Neuron 5614 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.9508. Min Range: -1.9508

Max Act: 1.9508. Min Act: -0.0002

Data Index: 1347819 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 1.9508. Min Range: -1.9508

Max Act: 1.7902. Min Act: -0.0002

Data Index: 175245 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 1.9508. Min Range: -1.9508

Max Act: 1.7107. Min Act: -0.0003

Data Index: 1086239 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 1.9508. Min Range: -1.9508

Max Act: 1.5949. Min Act: -0.0002

Data Index: 404060 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 1.9508. Min Range: -1.9508

Max Act: 1.4850. Min Act: -0.0002

Data Index: 552573 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 1.9508. Min Range: -1.9508

Max Act: 1.4687. Min Act: -0.0002

Data Index: 737297 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 1.9508. Min Range: -1.9508

Max Act: 1.3200. Min Act: -0.0002

Data Index: 995138 (C4 (Web Text))

Max Activating Token Index: 497

Text #7

Max Range: 1.9508. Min Range: -1.9508

Max Act: 1.3408. Min Act: -0.0002

Data Index: 907289 (C4 (Web Text))

Max Activating Token Index: 279

Text #8

Max Range: 1.9508. Min Range: -1.9508

Max Act: 1.2917. Min Act: -0.0002

Data Index: 658646 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 1.9508. Min Range: -1.9508

Max Act: 1.3169. Min Act: -0.0002

Data Index: 984173 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 1.9508. Min Range: -1.9508

Max Act: 1.2451. Min Act: -0.0002

Data Index: 534924 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 1.9508. Min Range: -1.9508

Max Act: 1.2083. Min Act: -0.0002

Data Index: 770191 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 1.9508. Min Range: -1.9508

Max Act: 1.2335. Min Act: -0.0002

Data Index: 319353 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 1.9508. Min Range: -1.9508

Max Act: 1.2115. Min Act: -0.0002

Data Index: 129234 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 1.9508. Min Range: -1.9508

Max Act: 1.2077. Min Act: -0.0002

Data Index: 593410 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 1.9508. Min Range: -1.9508

Max Act: 1.1889. Min Act: -0.0002

Data Index: 981086 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 1.9508. Min Range: -1.9508

Max Act: 1.1979. Min Act: -0.0003

Data Index: 1033356 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 1.9508. Min Range: -1.9508

Max Act: 1.1835. Min Act: -0.0002

Data Index: 550428 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 1.9508. Min Range: -1.9508

Max Act: 1.2078. Min Act: -0.0002

Data Index: 512123 (C4 (Web Text))

Max Activating Token Index: 687

Text #19

Max Range: 1.9508. Min Range: -1.9508

Max Act: 1.1810. Min Act: -0.0002

Data Index: 297026 (C4 (Web Text))

Max Activating Token Index: 72