Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2531 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0006. Min Act: -0.0002

Data Index: 1382997 (Python Code)

Max Activating Token Index: 972

Text #1

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0003. Min Act: -0.0002

Data Index: 1637525 (Python Code)

Max Activating Token Index: 957

Text #2

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0001. Min Act: -0.0003

Data Index: 310155 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0002. Min Act: -0.0003

Data Index: 683984 (C4 (Web Text))

Max Activating Token Index: 1022

Text #4

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1495930 (Python Code)

Max Activating Token Index: 971

Text #5

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0001. Min Act: -0.0003

Data Index: 200987 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1446454 (Python Code)

Max Activating Token Index: 998

Text #7

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1642888 (Python Code)

Max Activating Token Index: 970

Text #8

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1457739 (Python Code)

Max Activating Token Index: 1020

Text #9

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1564281 (Python Code)

Max Activating Token Index: 932

Text #10

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1410631 (Python Code)

Max Activating Token Index: 965

Text #11

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1542452 (Python Code)

Max Activating Token Index: 983

Text #12

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1595365 (Python Code)

Max Activating Token Index: 917

Text #13

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0001. Min Act: -0.0003

Data Index: 636745 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0001. Min Act: -0.0003

Data Index: 596254 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0001. Min Act: -0.0003

Data Index: 601523 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0001. Min Act: -0.0003

Data Index: 1258179 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1417475 (Python Code)

Max Activating Token Index: 995

Text #18

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1590609 (Python Code)

Max Activating Token Index: 1000

Text #19

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1382127 (Python Code)

Max Activating Token Index: 908