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

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

Neuron 215 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: 2.0022. Min Range: -2.0022

Max Act: 2.0022. Min Act: -0.0002

Data Index: 172345 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 2.0022. Min Range: -2.0022

Max Act: 1.8606. Min Act: -0.0002

Data Index: 363716 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 2.0022. Min Range: -2.0022

Max Act: 1.8124. Min Act: -0.0002

Data Index: 43481 (C4 (Web Text))

Max Activating Token Index: 444

Text #3

Max Range: 2.0022. Min Range: -2.0022

Max Act: 1.7397. Min Act: -0.0002

Data Index: 1235768 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 2.0022. Min Range: -2.0022

Max Act: 1.7067. Min Act: -0.0002

Data Index: 664807 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 2.0022. Min Range: -2.0022

Max Act: 1.5759. Min Act: -0.0002

Data Index: 733957 (C4 (Web Text))

Max Activating Token Index: 844

Text #6

Max Range: 2.0022. Min Range: -2.0022

Max Act: 1.6039. Min Act: -0.0002

Data Index: 900226 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 2.0022. Min Range: -2.0022

Max Act: 1.5341. Min Act: -0.0002

Data Index: 347195 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 2.0022. Min Range: -2.0022

Max Act: 1.5855. Min Act: -0.0002

Data Index: 391414 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 2.0022. Min Range: -2.0022

Max Act: 1.5123. Min Act: -0.0002

Data Index: 170862 (C4 (Web Text))

Max Activating Token Index: 810

Text #10

Max Range: 2.0022. Min Range: -2.0022

Max Act: 1.5299. Min Act: -0.0002

Data Index: 129165 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 2.0022. Min Range: -2.0022

Max Act: 1.5340. Min Act: -0.0002

Data Index: 1130760 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 2.0022. Min Range: -2.0022

Max Act: 1.4697. Min Act: -0.0002

Data Index: 516539 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 2.0022. Min Range: -2.0022

Max Act: 1.4404. Min Act: -0.0002

Data Index: 908530 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 2.0022. Min Range: -2.0022

Max Act: 1.4904. Min Act: -0.0002

Data Index: 609712 (C4 (Web Text))

Max Activating Token Index: 625

Text #15

Max Range: 2.0022. Min Range: -2.0022

Max Act: 1.4422. Min Act: -0.0002

Data Index: 323139 (C4 (Web Text))

Max Activating Token Index: 472

Text #16

Max Range: 2.0022. Min Range: -2.0022

Max Act: 1.4475. Min Act: -0.0002

Data Index: 1167259 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 2.0022. Min Range: -2.0022

Max Act: 1.4675. Min Act: -0.0002

Data Index: 404762 (C4 (Web Text))

Max Activating Token Index: 616

Text #18

Max Range: 2.0022. Min Range: -2.0022

Max Act: 1.4503. Min Act: -0.0002

Data Index: 1086922 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 2.0022. Min Range: -2.0022

Max Act: 1.4150. Min Act: -0.0003

Data Index: 434820 (C4 (Web Text))

Max Activating Token Index: 321