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

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

Neuron 285 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4812. Min Range: -0.4812

Max Act: 0.4812. Min Act: -0.0000

Data Index: 956252 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 0.4812. Min Range: -0.4812

Max Act: 0.4728. Min Act: -0.0000

Data Index: 379710 (C4 (Web Text))

Max Activating Token Index: 512

Text #2

Max Range: 0.4812. Min Range: -0.4812

Max Act: 0.4636. Min Act: -0.0000

Data Index: 544826 (C4 (Web Text))

Max Activating Token Index: 386

Text #3

Max Range: 0.4812. Min Range: -0.4812

Max Act: 0.4277. Min Act: -0.0000

Data Index: 926300 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 0.4812. Min Range: -0.4812

Max Act: 0.4194. Min Act: -0.0000

Data Index: 971306 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 0.4812. Min Range: -0.4812

Max Act: 0.4237. Min Act: -0.0000

Data Index: 847035 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 0.4812. Min Range: -0.4812

Max Act: 0.4276. Min Act: -0.0000

Data Index: 1522264 (Python Code)

Max Activating Token Index: 881

Text #7

Max Range: 0.4812. Min Range: -0.4812

Max Act: 0.4238. Min Act: -0.0000

Data Index: 994481 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 0.4812. Min Range: -0.4812

Max Act: 0.4150. Min Act: -0.0000

Data Index: 677405 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 0.4812. Min Range: -0.4812

Max Act: 0.3753. Min Act: -0.0000

Data Index: 153295 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 0.4812. Min Range: -0.4812

Max Act: 0.3778. Min Act: -0.0000

Data Index: 1153371 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 0.4812. Min Range: -0.4812

Max Act: 0.3870. Min Act: -0.0000

Data Index: 1522913 (Python Code)

Max Activating Token Index: 300

Text #12

Max Range: 0.4812. Min Range: -0.4812

Max Act: 0.3872. Min Act: -0.0000

Data Index: 809239 (C4 (Web Text))

Max Activating Token Index: 635

Text #13

Max Range: 0.4812. Min Range: -0.4812

Max Act: 0.3548. Min Act: -0.0000

Data Index: 469329 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 0.4812. Min Range: -0.4812

Max Act: 0.3892. Min Act: -0.0000

Data Index: 451959 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 0.4812. Min Range: -0.4812

Max Act: 0.3858. Min Act: -0.0000

Data Index: 458140 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 0.4812. Min Range: -0.4812

Max Act: 0.3865. Min Act: -0.0000

Data Index: 6515 (C4 (Web Text))

Max Activating Token Index: 312

Text #17

Max Range: 0.4812. Min Range: -0.4812

Max Act: 0.3726. Min Act: -0.0000

Data Index: 268080 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 0.4812. Min Range: -0.4812

Max Act: 0.3697. Min Act: -0.0000

Data Index: 35688 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 0.4812. Min Range: -0.4812

Max Act: 0.3586. Min Act: -0.0000

Data Index: 980325 (C4 (Web Text))

Max Activating Token Index: 182