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

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

Neuron 5707 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0680. Min Range: -1.0680

Max Act: 1.0680. Min Act: -0.0000

Data Index: 1213254 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.9877. Min Act: -0.0000

Data Index: 827591 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.9563. Min Act: -0.0000

Data Index: 1168461 (C4 (Web Text))

Max Activating Token Index: 925

Text #3

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.9481. Min Act: -0.0000

Data Index: 1105274 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.8639. Min Act: -0.0000

Data Index: 104000 (C4 (Web Text))

Max Activating Token Index: 681

Text #5

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.7644. Min Act: -0.0000

Data Index: 86132 (C4 (Web Text))

Max Activating Token Index: 482

Text #6

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.7602. Min Act: -0.0000

Data Index: 106685 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.7002. Min Act: -0.0000

Data Index: 1209931 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.7029. Min Act: -0.0000

Data Index: 9416 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.6930. Min Act: 0.0001

Data Index: 245502 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.6944. Min Act: -0.0000

Data Index: 1006311 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.6747. Min Act: -0.0000

Data Index: 1233868 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.6363. Min Act: -0.0000

Data Index: 897686 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.6775. Min Act: -0.0000

Data Index: 823082 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.6428. Min Act: 0.0000

Data Index: 102596 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.6490. Min Act: -0.0000

Data Index: 1588119 (Python Code)

Max Activating Token Index: 959

Text #16

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.6286. Min Act: -0.0000

Data Index: 596450 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.6235. Min Act: -0.0000

Data Index: 477764 (C4 (Web Text))

Max Activating Token Index: 696

Text #18

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.5616. Min Act: -0.0000

Data Index: 598224 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 1.0680. Min Range: -1.0680

Max Act: 0.5923. Min Act: -0.0000

Data Index: 817131 (C4 (Web Text))

Max Activating Token Index: 655