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

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

Neuron 3512 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3369. Min Range: -1.3369

Max Act: 1.3032. Min Act: -0.0002

Data Index: 532019 (C4 (Web Text))

Max Activating Token Index: 326

Text #1

Max Range: 1.3369. Min Range: -1.3369

Max Act: 1.3318. Min Act: -0.0002

Data Index: 1147592 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 1.3369. Min Range: -1.3369

Max Act: 1.2317. Min Act: -0.0002

Data Index: 1259989 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 1.3369. Min Range: -1.3369

Max Act: 1.0987. Min Act: -0.0002

Data Index: 720819 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 1.3369. Min Range: -1.3369

Max Act: 1.1696. Min Act: -0.0002

Data Index: 293796 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 1.3369. Min Range: -1.3369

Max Act: 1.3369. Min Act: -0.0002

Data Index: 7663 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 1.3369. Min Range: -1.3369

Max Act: 1.1869. Min Act: -0.0002

Data Index: 371831 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 1.3369. Min Range: -1.3369

Max Act: 0.9777. Min Act: -0.0002

Data Index: 677147 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 1.3369. Min Range: -1.3369

Max Act: 1.0954. Min Act: -0.0002

Data Index: 1269713 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 1.3369. Min Range: -1.3369

Max Act: 1.0827. Min Act: -0.0002

Data Index: 152951 (C4 (Web Text))

Max Activating Token Index: 961

Text #10

Max Range: 1.3369. Min Range: -1.3369

Max Act: 1.0198. Min Act: -0.0002

Data Index: 1339517 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 1.3369. Min Range: -1.3369

Max Act: 1.0839. Min Act: -0.0002

Data Index: 796221 (C4 (Web Text))

Max Activating Token Index: 394

Text #12

Max Range: 1.3369. Min Range: -1.3369

Max Act: 0.9861. Min Act: -0.0002

Data Index: 37039 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 1.3369. Min Range: -1.3369

Max Act: 0.9792. Min Act: -0.0002

Data Index: 1279987 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 1.3369. Min Range: -1.3369

Max Act: 1.0944. Min Act: -0.0002

Data Index: 778904 (C4 (Web Text))

Max Activating Token Index: 834

Text #15

Max Range: 1.3369. Min Range: -1.3369

Max Act: 1.0081. Min Act: -0.0002

Data Index: 291814 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 1.3369. Min Range: -1.3369

Max Act: 1.0220. Min Act: -0.0002

Data Index: 401341 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 1.3369. Min Range: -1.3369

Max Act: 0.9207. Min Act: -0.0002

Data Index: 378771 (C4 (Web Text))

Max Activating Token Index: 343

Text #18

Max Range: 1.3369. Min Range: -1.3369

Max Act: 1.0165. Min Act: -0.0002

Data Index: 1280943 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 1.3369. Min Range: -1.3369

Max Act: 0.9797. Min Act: -0.0002

Data Index: 296267 (C4 (Web Text))

Max Activating Token Index: 890