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

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

Neuron 4872 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3871. Min Range: -0.3871

Max Act: 0.3851. Min Act: -0.0000

Data Index: 757943 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 0.3871. Min Range: -0.3871

Max Act: 0.3499. Min Act: -0.0000

Data Index: 611261 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 0.3871. Min Range: -0.3871

Max Act: 0.3423. Min Act: -0.0000

Data Index: 646511 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 0.3871. Min Range: -0.3871

Max Act: 0.3871. Min Act: -0.0000

Data Index: 691664 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 0.3871. Min Range: -0.3871

Max Act: 0.3574. Min Act: -0.0000

Data Index: 1235430 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 0.3871. Min Range: -0.3871

Max Act: 0.3535. Min Act: -0.0000

Data Index: 718431 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 0.3871. Min Range: -0.3871

Max Act: 0.3373. Min Act: -0.0000

Data Index: 131514 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 0.3871. Min Range: -0.3871

Max Act: 0.3229. Min Act: -0.0000

Data Index: 43935 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 0.3871. Min Range: -0.3871

Max Act: 0.3119. Min Act: -0.0000

Data Index: 1051039 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 0.3871. Min Range: -0.3871

Max Act: 0.3294. Min Act: -0.0000

Data Index: 459551 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 0.3871. Min Range: -0.3871

Max Act: 0.3150. Min Act: -0.0000

Data Index: 422243 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 0.3871. Min Range: -0.3871

Max Act: 0.2996. Min Act: -0.0000

Data Index: 451971 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 0.3871. Min Range: -0.3871

Max Act: 0.3019. Min Act: -0.0000

Data Index: 154346 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 0.3871. Min Range: -0.3871

Max Act: 0.2982. Min Act: -0.0000

Data Index: 642590 (C4 (Web Text))

Max Activating Token Index: 193

Text #14

Max Range: 0.3871. Min Range: -0.3871

Max Act: 0.2947. Min Act: -0.0000

Data Index: 523645 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 0.3871. Min Range: -0.3871

Max Act: 0.2914. Min Act: -0.0000

Data Index: 221939 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 0.3871. Min Range: -0.3871

Max Act: 0.3004. Min Act: -0.0000

Data Index: 1338428 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 0.3871. Min Range: -0.3871

Max Act: 0.2902. Min Act: -0.0000

Data Index: 241641 (C4 (Web Text))

Max Activating Token Index: 807

Text #18

Max Range: 0.3871. Min Range: -0.3871

Max Act: 0.2984. Min Act: -0.0000

Data Index: 169864 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 0.3871. Min Range: -0.3871

Max Act: 0.2763. Min Act: -0.0000

Data Index: 502525 (C4 (Web Text))

Max Activating Token Index: 235