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

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

Neuron 1893 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: 0.0090. Min Range: -0.0090

Max Act: 0.0090. Min Act: -0.0006

Data Index: 1582299 (Python Code)

Max Activating Token Index: 1017

Text #1

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0082. Min Act: -0.0006

Data Index: 1574239 (Python Code)

Max Activating Token Index: 447

Text #2

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0078. Min Act: -0.0006

Data Index: 175442 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0076. Min Act: -0.0006

Data Index: 395491 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0077. Min Act: -0.0006

Data Index: 236590 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0070. Min Act: -0.0006

Data Index: 1514255 (Python Code)

Max Activating Token Index: 988

Text #6

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0069. Min Act: -0.0006

Data Index: 355528 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0069. Min Act: -0.0006

Data Index: 935780 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0069. Min Act: -0.0006

Data Index: 1506215 (Python Code)

Max Activating Token Index: 1002

Text #9

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0068. Min Act: -0.0006

Data Index: 899259 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0069. Min Act: -0.0006

Data Index: 997751 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0068. Min Act: -0.0006

Data Index: 571638 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0068. Min Act: -0.0006

Data Index: 1100922 (C4 (Web Text))

Max Activating Token Index: 376

Text #13

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0068. Min Act: -0.0006

Data Index: 253002 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0067. Min Act: -0.0005

Data Index: 1386374 (Python Code)

Max Activating Token Index: 916

Text #15

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0067. Min Act: -0.0006

Data Index: 1637484 (Python Code)

Max Activating Token Index: 981

Text #16

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0066. Min Act: -0.0006

Data Index: 543957 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0067. Min Act: -0.0006

Data Index: 1486393 (Python Code)

Max Activating Token Index: 704

Text #18

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0067. Min Act: -0.0006

Data Index: 247303 (C4 (Web Text))

Max Activating Token Index: 1011

Text #19

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0065. Min Act: -0.0006

Data Index: 762558 (C4 (Web Text))

Max Activating Token Index: 965