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

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

Neuron 455 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1368. Min Act: -0.0002

Data Index: 752286 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1066. Min Act: -0.0002

Data Index: 291424 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0901. Min Act: -0.0002

Data Index: 1212676 (C4 (Web Text))

Max Activating Token Index: 248

Text #3

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0866. Min Act: -0.0002

Data Index: 24481 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0862. Min Act: -0.0002

Data Index: 1142179 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0864. Min Act: -0.0002

Data Index: 49734 (C4 (Web Text))

Max Activating Token Index: 535

Text #6

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0861. Min Act: -0.0002

Data Index: 1287192 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0843. Min Act: -0.0002

Data Index: 1197459 (C4 (Web Text))

Max Activating Token Index: 568

Text #8

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0789. Min Act: -0.0002

Data Index: 397209 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0831. Min Act: -0.0001

Data Index: 276863 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0813. Min Act: -0.0002

Data Index: 973062 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0815. Min Act: -0.0001

Data Index: 545509 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0813. Min Act: -0.0002

Data Index: 599881 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0824. Min Act: -0.0002

Data Index: 266130 (C4 (Web Text))

Max Activating Token Index: 913

Text #14

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0810. Min Act: -0.0002

Data Index: 797146 (C4 (Web Text))

Max Activating Token Index: 526

Text #15

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0762. Min Act: -0.0002

Data Index: 423685 (C4 (Web Text))

Max Activating Token Index: 1022

Text #16

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0810. Min Act: -0.0002

Data Index: 212959 (C4 (Web Text))

Max Activating Token Index: 835

Text #17

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0784. Min Act: -0.0002

Data Index: 568239 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0793. Min Act: -0.0002

Data Index: 1293986 (C4 (Web Text))

Max Activating Token Index: 62

Text #19

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0762. Min Act: -0.0002

Data Index: 1345628 (C4 (Web Text))

Max Activating Token Index: 605