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

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

Neuron 1988 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: 0.4609. Min Range: -0.4609

Max Act: 0.4609. Min Act: -0.0005

Data Index: 756652 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.4048. Min Act: -0.0004

Data Index: 637459 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3430. Min Act: -0.0005

Data Index: 1043033 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3371. Min Act: -0.0005

Data Index: 931147 (C4 (Web Text))

Max Activating Token Index: 641

Text #4

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3311. Min Act: -0.0004

Data Index: 1205980 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3365. Min Act: -0.0005

Data Index: 309272 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3381. Min Act: -0.0005

Data Index: 924196 (C4 (Web Text))

Max Activating Token Index: 669

Text #7

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3014. Min Act: -0.0005

Data Index: 880055 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.2809. Min Act: -0.0005

Data Index: 24206 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3080. Min Act: -0.0005

Data Index: 608662 (C4 (Web Text))

Max Activating Token Index: 397

Text #10

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3048. Min Act: -0.0005

Data Index: 453901 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3178. Min Act: -0.0005

Data Index: 1174417 (C4 (Web Text))

Max Activating Token Index: 269

Text #12

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3056. Min Act: -0.0005

Data Index: 1313965 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3234. Min Act: -0.0005

Data Index: 559089 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3023. Min Act: -0.0005

Data Index: 1267547 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.2871. Min Act: -0.0005

Data Index: 924763 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.3077. Min Act: -0.0005

Data Index: 1214954 (C4 (Web Text))

Max Activating Token Index: 441

Text #17

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.2649. Min Act: -0.0005

Data Index: 1150206 (C4 (Web Text))

Max Activating Token Index: 444

Text #18

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.2853. Min Act: -0.0005

Data Index: 514490 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 0.4609. Min Range: -0.4609

Max Act: 0.2888. Min Act: -0.0005

Data Index: 887126 (C4 (Web Text))

Max Activating Token Index: 906