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

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

Neuron 731 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0073. Min Act: -0.0006

Data Index: 766658 (C4 (Web Text))

Max Activating Token Index: 493

Text #1

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0069. Min Act: -0.0006

Data Index: 105415 (C4 (Web Text))

Max Activating Token Index: 641

Text #2

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0068. Min Act: -0.0006

Data Index: 680197 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0066. Min Act: -0.0006

Data Index: 256976 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0067. Min Act: -0.0006

Data Index: 72182 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0065. Min Act: -0.0006

Data Index: 1424122 (Python Code)

Max Activating Token Index: 71

Text #6

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0066. Min Act: -0.0006

Data Index: 697449 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0065. Min Act: -0.0006

Data Index: 496760 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0064. Min Act: -0.0006

Data Index: 64661 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0062. Min Act: -0.0006

Data Index: 289268 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0064. Min Act: -0.0006

Data Index: 474231 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0063. Min Act: -0.0006

Data Index: 1279731 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0061. Min Act: -0.0006

Data Index: 227789 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0060. Min Act: -0.0006

Data Index: 540540 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0059. Min Act: -0.0006

Data Index: 987001 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0065. Min Act: -0.0006

Data Index: 462670 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0062. Min Act: -0.0006

Data Index: 968600 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0060. Min Act: -0.0006

Data Index: 341967 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0061. Min Act: -0.0006

Data Index: 556414 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0062. Min Act: -0.0006

Data Index: 739335 (C4 (Web Text))

Max Activating Token Index: 898