Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4169 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1250. Min Act: -0.0001

Data Index: 1078623 (C4 (Web Text))

Max Activating Token Index: 299

Text #1

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1191. Min Act: -0.0001

Data Index: 810960 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1067. Min Act: -0.0001

Data Index: 648188 (C4 (Web Text))

Max Activating Token Index: 499

Text #3

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1044. Min Act: -0.0001

Data Index: 309956 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.0949. Min Act: -0.0001

Data Index: 538260 (C4 (Web Text))

Max Activating Token Index: 212

Text #5

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1017. Min Act: -0.0001

Data Index: 1308091 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.0993. Min Act: -0.0001

Data Index: 370774 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.1033. Min Act: -0.0001

Data Index: 200064 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.0927. Min Act: -0.0001

Data Index: 1254099 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.0943. Min Act: -0.0001

Data Index: 866019 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.0884. Min Act: -0.0001

Data Index: 1454661 (Python Code)

Max Activating Token Index: 21

Text #11

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.0997. Min Act: -0.0001

Data Index: 1641570 (Python Code)

Max Activating Token Index: 941

Text #12

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.0828. Min Act: -0.0001

Data Index: 974813 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.0924. Min Act: -0.0001

Data Index: 1112807 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.0821. Min Act: -0.0001

Data Index: 343925 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.0789. Min Act: -0.0001

Data Index: 948920 (C4 (Web Text))

Max Activating Token Index: 599

Text #16

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.0906. Min Act: -0.0001

Data Index: 1038349 (C4 (Web Text))

Max Activating Token Index: 423

Text #17

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.0859. Min Act: -0.0001

Data Index: 1614321 (Python Code)

Max Activating Token Index: 86

Text #18

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.0852. Min Act: -0.0001

Data Index: 1525764 (Python Code)

Max Activating Token Index: 30

Text #19

Max Range: 0.1250. Min Range: -0.1250

Max Act: 0.0896. Min Act: -0.0001

Data Index: 1519847 (Python Code)

Max Activating Token Index: 18