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

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

Neuron 2063 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: 0.3998. Min Range: -0.3998

Max Act: 0.3998. Min Act: -0.0000

Data Index: 573447 (C4 (Web Text))

Max Activating Token Index: 370

Text #1

Max Range: 0.3998. Min Range: -0.3998

Max Act: 0.3402. Min Act: -0.0000

Data Index: 725707 (C4 (Web Text))

Max Activating Token Index: 604

Text #2

Max Range: 0.3998. Min Range: -0.3998

Max Act: 0.3398. Min Act: -0.0000

Data Index: 1140769 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 0.3998. Min Range: -0.3998

Max Act: 0.3344. Min Act: -0.0000

Data Index: 43068 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 0.3998. Min Range: -0.3998

Max Act: 0.3274. Min Act: -0.0000

Data Index: 590082 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 0.3998. Min Range: -0.3998

Max Act: 0.3250. Min Act: -0.0000

Data Index: 890672 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 0.3998. Min Range: -0.3998

Max Act: 0.3073. Min Act: -0.0000

Data Index: 823307 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 0.3998. Min Range: -0.3998

Max Act: 0.3129. Min Act: -0.0000

Data Index: 91245 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 0.3998. Min Range: -0.3998

Max Act: 0.3005. Min Act: -0.0000

Data Index: 276403 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 0.3998. Min Range: -0.3998

Max Act: 0.3028. Min Act: -0.0000

Data Index: 634470 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 0.3998. Min Range: -0.3998

Max Act: 0.3114. Min Act: -0.0000

Data Index: 45801 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 0.3998. Min Range: -0.3998

Max Act: 0.3099. Min Act: -0.0000

Data Index: 29083 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 0.3998. Min Range: -0.3998

Max Act: 0.3010. Min Act: -0.0000

Data Index: 97534 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 0.3998. Min Range: -0.3998

Max Act: 0.3213. Min Act: -0.0000

Data Index: 464168 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 0.3998. Min Range: -0.3998

Max Act: 0.2955. Min Act: -0.0000

Data Index: 1143980 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 0.3998. Min Range: -0.3998

Max Act: 0.2947. Min Act: -0.0000

Data Index: 1081812 (C4 (Web Text))

Max Activating Token Index: 806

Text #16

Max Range: 0.3998. Min Range: -0.3998

Max Act: 0.3033. Min Act: -0.0000

Data Index: 502151 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 0.3998. Min Range: -0.3998

Max Act: 0.3145. Min Act: -0.0000

Data Index: 755905 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 0.3998. Min Range: -0.3998

Max Act: 0.2836. Min Act: -0.0000

Data Index: 979647 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 0.3998. Min Range: -0.3998

Max Act: 0.2852. Min Act: -0.0000

Data Index: 1219905 (C4 (Web Text))

Max Activating Token Index: 379