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

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

Neuron 5707 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.3192. Min Act: -0.0000

Data Index: 1333757 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2778. Min Act: -0.0000

Data Index: 164089 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2432. Min Act: -0.0000

Data Index: 910338 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2318. Min Act: -0.0000

Data Index: 1180490 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2263. Min Act: -0.0000

Data Index: 521831 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2386. Min Act: -0.0000

Data Index: 416914 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2260. Min Act: -0.0000

Data Index: 330056 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2101. Min Act: -0.0000

Data Index: 3822 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2134. Min Act: -0.0000

Data Index: 297430 (C4 (Web Text))

Max Activating Token Index: 356

Text #9

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2011. Min Act: -0.0000

Data Index: 892510 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2141. Min Act: -0.0000

Data Index: 1328241 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2027. Min Act: -0.0000

Data Index: 238239 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.1944. Min Act: -0.0000

Data Index: 546020 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.1887. Min Act: -0.0000

Data Index: 320807 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.1881. Min Act: -0.0000

Data Index: 890970 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.1990. Min Act: -0.0000

Data Index: 1132906 (C4 (Web Text))

Max Activating Token Index: 252

Text #16

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2057. Min Act: -0.0000

Data Index: 654833 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.2140. Min Act: -0.0000

Data Index: 889695 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.1814. Min Act: -0.0000

Data Index: 643902 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 0.3192. Min Range: -0.3192

Max Act: 0.1891. Min Act: -0.0000

Data Index: 870487 (C4 (Web Text))

Max Activating Token Index: 995