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

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

Neuron 151 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1014. Min Range: -4.1014

Max Act: 4.1014. Min Act: -0.0000

Data Index: 430589 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 4.1014. Min Range: -4.1014

Max Act: 3.6199. Min Act: -0.0000

Data Index: 503247 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 4.1014. Min Range: -4.1014

Max Act: 3.3920. Min Act: -0.0000

Data Index: 1253836 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 4.1014. Min Range: -4.1014

Max Act: 3.1556. Min Act: -0.0000

Data Index: 274028 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 4.1014. Min Range: -4.1014

Max Act: 3.1111. Min Act: -0.0000

Data Index: 62942 (C4 (Web Text))

Max Activating Token Index: 458

Text #5

Max Range: 4.1014. Min Range: -4.1014

Max Act: 2.9250. Min Act: -0.0000

Data Index: 593350 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 4.1014. Min Range: -4.1014

Max Act: 2.8645. Min Act: -0.0000

Data Index: 1070014 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 4.1014. Min Range: -4.1014

Max Act: 2.9494. Min Act: -0.0001

Data Index: 276878 (C4 (Web Text))

Max Activating Token Index: 450

Text #8

Max Range: 4.1014. Min Range: -4.1014

Max Act: 2.6388. Min Act: -0.0000

Data Index: 333083 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 4.1014. Min Range: -4.1014

Max Act: 2.4804. Min Act: -0.0000

Data Index: 1057439 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 4.1014. Min Range: -4.1014

Max Act: 2.3146. Min Act: -0.0000

Data Index: 25405 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 4.1014. Min Range: -4.1014

Max Act: 2.2922. Min Act: -0.0001

Data Index: 441821 (C4 (Web Text))

Max Activating Token Index: 912

Text #12

Max Range: 4.1014. Min Range: -4.1014

Max Act: 2.3484. Min Act: -0.0001

Data Index: 711569 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 4.1014. Min Range: -4.1014

Max Act: 2.1873. Min Act: -0.0000

Data Index: 302659 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 4.1014. Min Range: -4.1014

Max Act: 2.4304. Min Act: -0.0000

Data Index: 276165 (C4 (Web Text))

Max Activating Token Index: 393

Text #15

Max Range: 4.1014. Min Range: -4.1014

Max Act: 2.2635. Min Act: -0.0001

Data Index: 83896 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 4.1014. Min Range: -4.1014

Max Act: 1.8847. Min Act: -0.0000

Data Index: 276857 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 4.1014. Min Range: -4.1014

Max Act: 2.2086. Min Act: -0.0000

Data Index: 206707 (C4 (Web Text))

Max Activating Token Index: 401

Text #18

Max Range: 4.1014. Min Range: -4.1014

Max Act: 2.4073. Min Act: -0.0000

Data Index: 809299 (C4 (Web Text))

Max Activating Token Index: 891

Text #19

Max Range: 4.1014. Min Range: -4.1014

Max Act: 2.3996. Min Act: -0.0001

Data Index: 792405 (C4 (Web Text))

Max Activating Token Index: 252