Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1424 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.1086. Min Act: -0.0003

Data Index: 140412 (C4 (Web Text))

Max Activating Token Index: 295

Text #1

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0995. Min Act: -0.0003

Data Index: 1003202 (C4 (Web Text))

Max Activating Token Index: 892

Text #2

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0958. Min Act: -0.0003

Data Index: 1006080 (C4 (Web Text))

Max Activating Token Index: 426

Text #3

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0952. Min Act: -0.0003

Data Index: 426644 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0950. Min Act: -0.0003

Data Index: 1171324 (C4 (Web Text))

Max Activating Token Index: 565

Text #5

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0917. Min Act: -0.0003

Data Index: 135365 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0900. Min Act: -0.0003

Data Index: 253088 (C4 (Web Text))

Max Activating Token Index: 645

Text #7

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0901. Min Act: -0.0003

Data Index: 717080 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0888. Min Act: -0.0003

Data Index: 848282 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0882. Min Act: -0.0003

Data Index: 127542 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0856. Min Act: -0.0003

Data Index: 1299258 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0847. Min Act: -0.0003

Data Index: 1187275 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0848. Min Act: -0.0004

Data Index: 857078 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0822. Min Act: -0.0003

Data Index: 373871 (C4 (Web Text))

Max Activating Token Index: 609

Text #14

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0822. Min Act: -0.0003

Data Index: 698593 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0821. Min Act: -0.0003

Data Index: 1187580 (C4 (Web Text))

Max Activating Token Index: 457

Text #16

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0818. Min Act: -0.0002

Data Index: 135983 (C4 (Web Text))

Max Activating Token Index: 788

Text #17

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0800. Min Act: -0.0003

Data Index: 1311237 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0787. Min Act: -0.0003

Data Index: 752071 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0784. Min Act: -0.0003

Data Index: 363118 (C4 (Web Text))

Max Activating Token Index: 563