Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 654 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1126. Min Act: -0.0001

Data Index: 857807 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1067. Min Act: -0.0001

Data Index: 1259745 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0960. Min Act: -0.0001

Data Index: 1008592 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1138. Min Act: -0.0001

Data Index: 747571 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1145. Min Act: -0.0001

Data Index: 376493 (C4 (Web Text))

Max Activating Token Index: 793

Text #5

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0915. Min Act: -0.0001

Data Index: 951086 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1034. Min Act: -0.0001

Data Index: 1274969 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1062. Min Act: -0.0001

Data Index: 465832 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0907. Min Act: -0.0001

Data Index: 342348 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0975. Min Act: -0.0001

Data Index: 1070318 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0577. Min Act: -0.0001

Data Index: 908764 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0812. Min Act: -0.0001

Data Index: 192541 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0914. Min Act: -0.0001

Data Index: 1198594 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0896. Min Act: -0.0001

Data Index: 1190038 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0960. Min Act: -0.0001

Data Index: 214066 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0950. Min Act: -0.0001

Data Index: 567515 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0861. Min Act: -0.0001

Data Index: 1155469 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0845. Min Act: -0.0001

Data Index: 1008873 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0943. Min Act: -0.0001

Data Index: 980408 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0850. Min Act: -0.0001

Data Index: 250244 (C4 (Web Text))

Max Activating Token Index: 226