Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2231 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0042. Min Act: -0.0003

Data Index: 569121 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0049. Min Act: -0.0003

Data Index: 2763 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0042. Min Act: -0.0003

Data Index: 9864 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0037. Min Act: -0.0003

Data Index: 1540135 (Python Code)

Max Activating Token Index: 2

Text #4

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0034. Min Act: -0.0003

Data Index: 1066284 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0033. Min Act: -0.0003

Data Index: 1017140 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0033. Min Act: -0.0003

Data Index: 1601084 (Python Code)

Max Activating Token Index: 3

Text #7

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0033. Min Act: -0.0003

Data Index: 697764 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0033. Min Act: -0.0003

Data Index: 1197581 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0032. Min Act: -0.0003

Data Index: 735167 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0034. Min Act: -0.0003

Data Index: 1260004 (C4 (Web Text))

Max Activating Token Index: 809

Text #11

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0033. Min Act: -0.0003

Data Index: 1076745 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0030. Min Act: -0.0003

Data Index: 376871 (C4 (Web Text))

Max Activating Token Index: 499

Text #13

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0034. Min Act: -0.0003

Data Index: 664369 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0029. Min Act: -0.0003

Data Index: 932061 (C4 (Web Text))

Max Activating Token Index: 616

Text #15

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0031. Min Act: -0.0003

Data Index: 642732 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0031. Min Act: -0.0003

Data Index: 464396 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0030. Min Act: -0.0003

Data Index: 794821 (C4 (Web Text))

Max Activating Token Index: 957

Text #18

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0032. Min Act: -0.0002

Data Index: 93443 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0030. Min Act: -0.0003

Data Index: 1355325 (C4 (Web Text))

Max Activating Token Index: 829