Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 627 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0040. Min Act: -0.0004

Data Index: 1606450 (Python Code)

Max Activating Token Index: 1017

Text #1

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0039. Min Act: -0.0004

Data Index: 1426708 (Python Code)

Max Activating Token Index: 988

Text #2

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0038. Min Act: -0.0004

Data Index: 1532720 (Python Code)

Max Activating Token Index: 974

Text #3

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0036. Min Act: -0.0003

Data Index: 1411617 (Python Code)

Max Activating Token Index: 721

Text #4

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0036. Min Act: -0.0004

Data Index: 1583054 (Python Code)

Max Activating Token Index: 978

Text #5

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0035. Min Act: -0.0004

Data Index: 1625881 (Python Code)

Max Activating Token Index: 1000

Text #6

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0035. Min Act: -0.0004

Data Index: 678687 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0035. Min Act: -0.0004

Data Index: 1418213 (Python Code)

Max Activating Token Index: 984

Text #8

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0035. Min Act: -0.0004

Data Index: 1390012 (Python Code)

Max Activating Token Index: 1012

Text #9

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0034. Min Act: -0.0004

Data Index: 1159096 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0034. Min Act: -0.0004

Data Index: 1425789 (Python Code)

Max Activating Token Index: 1019

Text #11

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0034. Min Act: -0.0004

Data Index: 1492522 (Python Code)

Max Activating Token Index: 968

Text #12

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0034. Min Act: -0.0004

Data Index: 1151118 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0034. Min Act: -0.0004

Data Index: 1250355 (C4 (Web Text))

Max Activating Token Index: 1014

Text #14

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0035. Min Act: -0.0004

Data Index: 1575887 (Python Code)

Max Activating Token Index: 993

Text #15

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0034. Min Act: -0.0004

Data Index: 1431863 (Python Code)

Max Activating Token Index: 964

Text #16

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0034. Min Act: -0.0004

Data Index: 1473979 (Python Code)

Max Activating Token Index: 921

Text #17

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0033. Min Act: -0.0004

Data Index: 1554449 (Python Code)

Max Activating Token Index: 899

Text #18

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0033. Min Act: -0.0004

Data Index: 1439606 (Python Code)

Max Activating Token Index: 1016

Text #19

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0034. Min Act: -0.0004

Data Index: 1653065 (Python Code)

Max Activating Token Index: 941