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

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

Neuron 3711 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: 0.2524. Min Range: -0.2524

Max Act: 0.2524. Min Act: -0.0000

Data Index: 741738 (C4 (Web Text))

Max Activating Token Index: 710

Text #1

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2393. Min Act: -0.0000

Data Index: 225663 (C4 (Web Text))

Max Activating Token Index: 625

Text #2

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2297. Min Act: -0.0000

Data Index: 1116357 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2190. Min Act: -0.0000

Data Index: 708617 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2079. Min Act: -0.0000

Data Index: 746053 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2030. Min Act: -0.0000

Data Index: 408347 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.1994. Min Act: -0.0000

Data Index: 1253906 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.1918. Min Act: -0.0000

Data Index: 713628 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.1891. Min Act: -0.0000

Data Index: 211930 (C4 (Web Text))

Max Activating Token Index: 877

Text #9

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.1932. Min Act: -0.0000

Data Index: 1174059 (C4 (Web Text))

Max Activating Token Index: 657

Text #10

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.1870. Min Act: -0.0000

Data Index: 374810 (C4 (Web Text))

Max Activating Token Index: 865

Text #11

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.1928. Min Act: -0.0000

Data Index: 8717 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.1859. Min Act: -0.0000

Data Index: 488990 (C4 (Web Text))

Max Activating Token Index: 459

Text #13

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.1904. Min Act: -0.0000

Data Index: 1154795 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.1866. Min Act: -0.0000

Data Index: 77567 (C4 (Web Text))

Max Activating Token Index: 108

Text #15

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.1840. Min Act: -0.0000

Data Index: 860818 (C4 (Web Text))

Max Activating Token Index: 989

Text #16

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.1834. Min Act: -0.0000

Data Index: 1258772 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.1871. Min Act: -0.0000

Data Index: 1021255 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.1858. Min Act: -0.0000

Data Index: 1008066 (C4 (Web Text))

Max Activating Token Index: 501

Text #19

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.1756. Min Act: -0.0000

Data Index: 461947 (C4 (Web Text))

Max Activating Token Index: 596