Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1883 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.1040. Min Act: -0.0002

Data Index: 1257518 (C4 (Web Text))

Max Activating Token Index: 355

Text #1

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0925. Min Act: -0.0003

Data Index: 500393 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0892. Min Act: -0.0002

Data Index: 824480 (C4 (Web Text))

Max Activating Token Index: 420

Text #3

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0986. Min Act: -0.0003

Data Index: 494919 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0758. Min Act: -0.0003

Data Index: 1292310 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0837. Min Act: -0.0002

Data Index: 1166935 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0802. Min Act: -0.0003

Data Index: 1287460 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0837. Min Act: -0.0002

Data Index: 587671 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0807. Min Act: -0.0003

Data Index: 249963 (C4 (Web Text))

Max Activating Token Index: 131

Text #9

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0799. Min Act: -0.0003

Data Index: 1081977 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0827. Min Act: -0.0002

Data Index: 832232 (C4 (Web Text))

Max Activating Token Index: 836

Text #11

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0763. Min Act: -0.0002

Data Index: 722887 (C4 (Web Text))

Max Activating Token Index: 246

Text #12

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0863. Min Act: -0.0002

Data Index: 734345 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0782. Min Act: -0.0002

Data Index: 888790 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0765. Min Act: -0.0003

Data Index: 1474637 (Python Code)

Max Activating Token Index: 379

Text #15

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0786. Min Act: -0.0003

Data Index: 601585 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0758. Min Act: -0.0003

Data Index: 760075 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0719. Min Act: -0.0002

Data Index: 1189168 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0658. Min Act: -0.0003

Data Index: 1000304 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0821. Min Act: -0.0002

Data Index: 340040 (C4 (Web Text))

Max Activating Token Index: 708