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

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

Neuron 396 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: 0.0065. Min Range: -0.0065

Max Act: 0.0065. Min Act: -0.0005

Data Index: 1533174 (Python Code)

Max Activating Token Index: 193

Text #1

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0063. Min Act: -0.0006

Data Index: 118937 (C4 (Web Text))

Max Activating Token Index: 775

Text #2

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0063. Min Act: -0.0005

Data Index: 1413208 (Python Code)

Max Activating Token Index: 18

Text #3

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0063. Min Act: -0.0006

Data Index: 1013843 (C4 (Web Text))

Max Activating Token Index: 510

Text #4

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0064. Min Act: -0.0006

Data Index: 494773 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0062. Min Act: -0.0006

Data Index: 556735 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0062. Min Act: -0.0006

Data Index: 462802 (C4 (Web Text))

Max Activating Token Index: 464

Text #7

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0061. Min Act: -0.0006

Data Index: 64925 (C4 (Web Text))

Max Activating Token Index: 673

Text #8

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0061. Min Act: -0.0006

Data Index: 880175 (C4 (Web Text))

Max Activating Token Index: 232

Text #9

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0061. Min Act: -0.0005

Data Index: 167837 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0061. Min Act: -0.0005

Data Index: 1654828 (Python Code)

Max Activating Token Index: 605

Text #11

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0060. Min Act: -0.0006

Data Index: 209425 (C4 (Web Text))

Max Activating Token Index: 628

Text #12

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0060. Min Act: -0.0006

Data Index: 117083 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0060. Min Act: -0.0004

Data Index: 1431044 (Python Code)

Max Activating Token Index: 5

Text #14

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0060. Min Act: -0.0006

Data Index: 1047296 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0060. Min Act: -0.0006

Data Index: 301501 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0059. Min Act: -0.0006

Data Index: 1012184 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0058. Min Act: -0.0005

Data Index: 1594858 (Python Code)

Max Activating Token Index: 5

Text #18

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0058. Min Act: -0.0006

Data Index: 360366 (C4 (Web Text))

Max Activating Token Index: 320

Text #19

Max Range: 0.0065. Min Range: -0.0065

Max Act: 0.0058. Min Act: -0.0006

Data Index: 1062696 (C4 (Web Text))

Max Activating Token Index: 308