Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 829 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0070. Min Act: -0.0006

Data Index: 7552 (C4 (Web Text))

Max Activating Token Index: 396

Text #1

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0070. Min Act: -0.0006

Data Index: 1069295 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0069. Min Act: -0.0006

Data Index: 209540 (C4 (Web Text))

Max Activating Token Index: 978

Text #3

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0069. Min Act: -0.0006

Data Index: 762863 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0068. Min Act: -0.0006

Data Index: 894729 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0066. Min Act: -0.0006

Data Index: 294462 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0067. Min Act: -0.0006

Data Index: 210415 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0068. Min Act: -0.0006

Data Index: 82487 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0067. Min Act: -0.0006

Data Index: 554689 (C4 (Web Text))

Max Activating Token Index: 657

Text #9

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0066. Min Act: -0.0006

Data Index: 545628 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0066. Min Act: -0.0006

Data Index: 509142 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0066. Min Act: -0.0006

Data Index: 109164 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0066. Min Act: -0.0006

Data Index: 1017600 (C4 (Web Text))

Max Activating Token Index: 339

Text #13

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0006

Data Index: 850432 (C4 (Web Text))

Max Activating Token Index: 605

Text #14

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0066. Min Act: -0.0006

Data Index: 1420435 (Python Code)

Max Activating Token Index: 656

Text #15

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0067. Min Act: -0.0006

Data Index: 259874 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0006

Data Index: 90996 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0066. Min Act: -0.0007

Data Index: 999237 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0005

Data Index: 1475867 (Python Code)

Max Activating Token Index: 790

Text #19

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0064. Min Act: -0.0006

Data Index: 855608 (C4 (Web Text))

Max Activating Token Index: 785