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

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

Neuron 2936 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1557. Min Act: -0.0000

Data Index: 360783 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1746. Min Act: -0.0000

Data Index: 845942 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1460. Min Act: -0.0000

Data Index: 423609 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1526. Min Act: -0.0000

Data Index: 1549282 (Python Code)

Max Activating Token Index: 782

Text #4

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1457. Min Act: -0.0000

Data Index: 137939 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1425. Min Act: -0.0000

Data Index: 85440 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1454. Min Act: -0.0000

Data Index: 58532 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1441. Min Act: -0.0000

Data Index: 1307751 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1259. Min Act: -0.0000

Data Index: 1337921 (C4 (Web Text))

Max Activating Token Index: 545

Text #9

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1178. Min Act: -0.0000

Data Index: 602422 (C4 (Web Text))

Max Activating Token Index: 385

Text #10

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1063. Min Act: -0.0000

Data Index: 1355885 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1093. Min Act: -0.0000

Data Index: 42692 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1128. Min Act: -0.0000

Data Index: 1127822 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1165. Min Act: -0.0000

Data Index: 557179 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1183. Min Act: -0.0000

Data Index: 296064 (C4 (Web Text))

Max Activating Token Index: 461

Text #15

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1116. Min Act: -0.0000

Data Index: 55040 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1070. Min Act: -0.0000

Data Index: 496864 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1033. Min Act: -0.0000

Data Index: 727059 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1112. Min Act: -0.0000

Data Index: 321472 (C4 (Web Text))

Max Activating Token Index: 598

Text #19

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1037. Min Act: -0.0000

Data Index: 875246 (C4 (Web Text))

Max Activating Token Index: 716