Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2596 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1303. Min Act: -0.0003

Data Index: 436797 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1152. Min Act: -0.0003

Data Index: 689471 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1116. Min Act: -0.0003

Data Index: 1347079 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1093. Min Act: -0.0003

Data Index: 1333906 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1146. Min Act: -0.0003

Data Index: 778421 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1060. Min Act: -0.0003

Data Index: 1046739 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1161. Min Act: -0.0003

Data Index: 564159 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1074. Min Act: -0.0003

Data Index: 253800 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1073. Min Act: -0.0003

Data Index: 191588 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1024. Min Act: -0.0003

Data Index: 535175 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1046. Min Act: -0.0003

Data Index: 1055703 (C4 (Web Text))

Max Activating Token Index: 303

Text #11

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1086. Min Act: -0.0003

Data Index: 307398 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1085. Min Act: -0.0003

Data Index: 511013 (C4 (Web Text))

Max Activating Token Index: 379

Text #13

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1072. Min Act: -0.0003

Data Index: 1058533 (C4 (Web Text))

Max Activating Token Index: 211

Text #14

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1069. Min Act: -0.0003

Data Index: 107333 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.0969. Min Act: -0.0003

Data Index: 778835 (C4 (Web Text))

Max Activating Token Index: 769

Text #16

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.0976. Min Act: -0.0003

Data Index: 1573479 (Python Code)

Max Activating Token Index: 37

Text #17

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.0973. Min Act: -0.0003

Data Index: 900940 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.0970. Min Act: -0.0003

Data Index: 1124469 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1001. Min Act: -0.0003

Data Index: 296471 (C4 (Web Text))

Max Activating Token Index: 198