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

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

Neuron 1983 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.1010. Min Act: -0.0001

Data Index: 1246831 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0943. Min Act: -0.0001

Data Index: 1318660 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0979. Min Act: -0.0001

Data Index: 739324 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0778. Min Act: -0.0001

Data Index: 805570 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0918. Min Act: -0.0001

Data Index: 734240 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0850. Min Act: -0.0001

Data Index: 310542 (C4 (Web Text))

Max Activating Token Index: 514

Text #6

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0836. Min Act: -0.0001

Data Index: 452975 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0861. Min Act: -0.0001

Data Index: 1004095 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0880. Min Act: -0.0001

Data Index: 1016503 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0850. Min Act: -0.0001

Data Index: 993954 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0785. Min Act: -0.0001

Data Index: 345868 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0869. Min Act: -0.0001

Data Index: 1299212 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0847. Min Act: -0.0001

Data Index: 165365 (C4 (Web Text))

Max Activating Token Index: 570

Text #13

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0777. Min Act: -0.0001

Data Index: 645885 (C4 (Web Text))

Max Activating Token Index: 344

Text #14

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0714. Min Act: -0.0001

Data Index: 1186394 (C4 (Web Text))

Max Activating Token Index: 677

Text #15

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0785. Min Act: -0.0001

Data Index: 228394 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0767. Min Act: -0.0001

Data Index: 1197036 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0842. Min Act: -0.0001

Data Index: 32299 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0737. Min Act: -0.0001

Data Index: 1043097 (C4 (Web Text))

Max Activating Token Index: 351

Text #19

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0733. Min Act: -0.0001

Data Index: 501599 (C4 (Web Text))

Max Activating Token Index: 466