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

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

Neuron 1050 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.1011. Min Act: -0.0002

Data Index: 357186 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0897. Min Act: -0.0002

Data Index: 555265 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0881. Min Act: -0.0002

Data Index: 678258 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0834. Min Act: -0.0002

Data Index: 1253027 (C4 (Web Text))

Max Activating Token Index: 297

Text #4

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0834. Min Act: -0.0002

Data Index: 1061028 (C4 (Web Text))

Max Activating Token Index: 471

Text #5

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0867. Min Act: -0.0002

Data Index: 289918 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0950. Min Act: -0.0002

Data Index: 557880 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0878. Min Act: -0.0002

Data Index: 343108 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0778. Min Act: -0.0002

Data Index: 532354 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0805. Min Act: -0.0002

Data Index: 170375 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0830. Min Act: -0.0002

Data Index: 409285 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0884. Min Act: -0.0002

Data Index: 1239138 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0788. Min Act: -0.0002

Data Index: 1310136 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0901. Min Act: -0.0002

Data Index: 1289141 (C4 (Web Text))

Max Activating Token Index: 287

Text #14

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0779. Min Act: -0.0002

Data Index: 346449 (C4 (Web Text))

Max Activating Token Index: 455

Text #15

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0799. Min Act: -0.0002

Data Index: 954465 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0784. Min Act: -0.0002

Data Index: 485578 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0744. Min Act: -0.0002

Data Index: 1157917 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0813. Min Act: -0.0002

Data Index: 51191 (C4 (Web Text))

Max Activating Token Index: 857

Text #19

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0797. Min Act: -0.0002

Data Index: 184958 (C4 (Web Text))

Max Activating Token Index: 334