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

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

Neuron 2019 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: 0.0976. Min Range: -0.0976

Max Act: 0.0939. Min Act: -0.0002

Data Index: 559878 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0976. Min Act: -0.0002

Data Index: 1292339 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0958. Min Act: -0.0002

Data Index: 1346350 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0946. Min Act: -0.0002

Data Index: 750090 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0944. Min Act: -0.0002

Data Index: 197323 (C4 (Web Text))

Max Activating Token Index: 939

Text #5

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0919. Min Act: -0.0002

Data Index: 1358841 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0874. Min Act: -0.0002

Data Index: 389549 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0872. Min Act: -0.0002

Data Index: 633192 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0894. Min Act: -0.0002

Data Index: 1262987 (C4 (Web Text))

Max Activating Token Index: 397

Text #9

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0871. Min Act: -0.0002

Data Index: 347964 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0894. Min Act: -0.0002

Data Index: 720837 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0850. Min Act: -0.0002

Data Index: 1217306 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0838. Min Act: -0.0002

Data Index: 174496 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0865. Min Act: -0.0002

Data Index: 129357 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0859. Min Act: -0.0002

Data Index: 724221 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0796. Min Act: -0.0002

Data Index: 528130 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0826. Min Act: -0.0002

Data Index: 128 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0819. Min Act: -0.0002

Data Index: 340213 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0854. Min Act: -0.0002

Data Index: 469026 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0820. Min Act: -0.0002

Data Index: 1032766 (C4 (Web Text))

Max Activating Token Index: 534