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

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

Neuron 1596 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: 0.1157. Min Range: -0.1157

Max Act: 0.1125. Min Act: -0.0005

Data Index: 981405 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1157. Min Act: -0.0005

Data Index: 260694 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1069. Min Act: -0.0005

Data Index: 577584 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1051. Min Act: -0.0005

Data Index: 777545 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0992. Min Act: -0.0005

Data Index: 962661 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0923. Min Act: -0.0005

Data Index: 252204 (C4 (Web Text))

Max Activating Token Index: 917

Text #6

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0909. Min Act: -0.0005

Data Index: 953440 (C4 (Web Text))

Max Activating Token Index: 559

Text #7

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0905. Min Act: -0.0005

Data Index: 1113421 (C4 (Web Text))

Max Activating Token Index: 865

Text #8

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0895. Min Act: -0.0005

Data Index: 1106752 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0865. Min Act: -0.0005

Data Index: 521 (C4 (Web Text))

Max Activating Token Index: 768

Text #10

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0862. Min Act: -0.0005

Data Index: 348036 (C4 (Web Text))

Max Activating Token Index: 996

Text #11

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0811. Min Act: -0.0005

Data Index: 786615 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0878. Min Act: -0.0005

Data Index: 509609 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0894. Min Act: -0.0005

Data Index: 677545 (C4 (Web Text))

Max Activating Token Index: 403

Text #14

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0830. Min Act: -0.0005

Data Index: 1087052 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0883. Min Act: -0.0005

Data Index: 650646 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0854. Min Act: -0.0005

Data Index: 1151854 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0875. Min Act: -0.0005

Data Index: 1264269 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0846. Min Act: -0.0005

Data Index: 1259585 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0835. Min Act: -0.0005

Data Index: 476965 (C4 (Web Text))

Max Activating Token Index: 181