Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 419 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.1050. Min Act: -0.0005

Data Index: 137945 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.1070. Min Act: -0.0005

Data Index: 182673 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.1086. Min Act: -0.0005

Data Index: 1359302 (C4 (Web Text))

Max Activating Token Index: 740

Text #3

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.1081. Min Act: -0.0005

Data Index: 1353609 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0972. Min Act: -0.0005

Data Index: 76304 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.1017. Min Act: -0.0005

Data Index: 51457 (C4 (Web Text))

Max Activating Token Index: 350

Text #6

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0958. Min Act: -0.0005

Data Index: 832218 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0858. Min Act: -0.0005

Data Index: 744183 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0836. Min Act: -0.0005

Data Index: 620711 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0851. Min Act: -0.0005

Data Index: 697025 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0871. Min Act: -0.0005

Data Index: 277122 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0817. Min Act: -0.0005

Data Index: 1128639 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0769. Min Act: -0.0005

Data Index: 693931 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0794. Min Act: -0.0005

Data Index: 1331329 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0777. Min Act: -0.0005

Data Index: 275444 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0794. Min Act: -0.0005

Data Index: 663593 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0715. Min Act: -0.0005

Data Index: 433389 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0767. Min Act: -0.0005

Data Index: 1140768 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0731. Min Act: -0.0005

Data Index: 388842 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0734. Min Act: -0.0005

Data Index: 1276707 (C4 (Web Text))

Max Activating Token Index: 146