Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1208 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.3876. Min Range: -0.3876

Max Act: 0.3876. Min Act: -0.0002

Data Index: 406889 (C4 (Web Text))

Max Activating Token Index: 295

Text #1

Max Range: 0.3876. Min Range: -0.3876

Max Act: 0.3454. Min Act: -0.0002

Data Index: 868614 (C4 (Web Text))

Max Activating Token Index: 276

Text #2

Max Range: 0.3876. Min Range: -0.3876

Max Act: 0.3739. Min Act: -0.0002

Data Index: 482998 (C4 (Web Text))

Max Activating Token Index: 444

Text #3

Max Range: 0.3876. Min Range: -0.3876

Max Act: 0.3501. Min Act: -0.0002

Data Index: 240254 (C4 (Web Text))

Max Activating Token Index: 496

Text #4

Max Range: 0.3876. Min Range: -0.3876

Max Act: 0.3253. Min Act: -0.0002

Data Index: 188883 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 0.3876. Min Range: -0.3876

Max Act: 0.3398. Min Act: -0.0002

Data Index: 584335 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 0.3876. Min Range: -0.3876

Max Act: 0.3385. Min Act: -0.0002

Data Index: 9953 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 0.3876. Min Range: -0.3876

Max Act: 0.3503. Min Act: -0.0002

Data Index: 20225 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 0.3876. Min Range: -0.3876

Max Act: 0.3387. Min Act: -0.0002

Data Index: 790926 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 0.3876. Min Range: -0.3876

Max Act: 0.3229. Min Act: -0.0002

Data Index: 198062 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 0.3876. Min Range: -0.3876

Max Act: 0.3327. Min Act: -0.0002

Data Index: 575551 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 0.3876. Min Range: -0.3876

Max Act: 0.3474. Min Act: -0.0002

Data Index: 580498 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 0.3876. Min Range: -0.3876

Max Act: 0.3426. Min Act: -0.0002

Data Index: 1257698 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 0.3876. Min Range: -0.3876

Max Act: 0.3332. Min Act: -0.0002

Data Index: 1175944 (C4 (Web Text))

Max Activating Token Index: 832

Text #14

Max Range: 0.3876. Min Range: -0.3876

Max Act: 0.3134. Min Act: -0.0002

Data Index: 760357 (C4 (Web Text))

Max Activating Token Index: 531

Text #15

Max Range: 0.3876. Min Range: -0.3876

Max Act: 0.3173. Min Act: -0.0002

Data Index: 392310 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 0.3876. Min Range: -0.3876

Max Act: 0.3383. Min Act: -0.0002

Data Index: 848756 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 0.3876. Min Range: -0.3876

Max Act: 0.3278. Min Act: -0.0002

Data Index: 542577 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 0.3876. Min Range: -0.3876

Max Act: 0.3065. Min Act: -0.0002

Data Index: 754444 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 0.3876. Min Range: -0.3876

Max Act: 0.3359. Min Act: -0.0002

Data Index: 75588 (C4 (Web Text))

Max Activating Token Index: 765