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

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

Neuron 5554 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: 3.7602. Min Range: -3.7602

Max Act: 3.7602. Min Act: -0.0000

Data Index: 293311 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 3.7602. Min Range: -3.7602

Max Act: 2.9951. Min Act: -0.0001

Data Index: 446681 (C4 (Web Text))

Max Activating Token Index: 559

Text #2

Max Range: 3.7602. Min Range: -3.7602

Max Act: 2.9712. Min Act: -0.0000

Data Index: 1157913 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 3.7602. Min Range: -3.7602

Max Act: 2.5064. Min Act: -0.0000

Data Index: 915701 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 3.7602. Min Range: -3.7602

Max Act: 2.4175. Min Act: -0.0000

Data Index: 309681 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 3.7602. Min Range: -3.7602

Max Act: 2.4676. Min Act: -0.0000

Data Index: 1133607 (C4 (Web Text))

Max Activating Token Index: 474

Text #6

Max Range: 3.7602. Min Range: -3.7602

Max Act: 2.1254. Min Act: -0.0000

Data Index: 23160 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 3.7602. Min Range: -3.7602

Max Act: 1.7430. Min Act: -0.0001

Data Index: 747787 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 3.7602. Min Range: -3.7602

Max Act: 1.8377. Min Act: -0.0000

Data Index: 349877 (C4 (Web Text))

Max Activating Token Index: 363

Text #9

Max Range: 3.7602. Min Range: -3.7602

Max Act: 1.7154. Min Act: -0.0000

Data Index: 325323 (C4 (Web Text))

Max Activating Token Index: 444

Text #10

Max Range: 3.7602. Min Range: -3.7602

Max Act: 1.6485. Min Act: -0.0000

Data Index: 1353195 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 3.7602. Min Range: -3.7602

Max Act: 1.5683. Min Act: -0.0000

Data Index: 288078 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 3.7602. Min Range: -3.7602

Max Act: 1.5704. Min Act: -0.0001

Data Index: 463924 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 3.7602. Min Range: -3.7602

Max Act: 1.5417. Min Act: -0.0001

Data Index: 328758 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 3.7602. Min Range: -3.7602

Max Act: 1.5364. Min Act: -0.0001

Data Index: 996418 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 3.7602. Min Range: -3.7602

Max Act: 1.5153. Min Act: -0.0001

Data Index: 1275518 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 3.7602. Min Range: -3.7602

Max Act: 1.5143. Min Act: -0.0000

Data Index: 445450 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 3.7602. Min Range: -3.7602

Max Act: 1.5622. Min Act: -0.0000

Data Index: 1300218 (C4 (Web Text))

Max Activating Token Index: 483

Text #18

Max Range: 3.7602. Min Range: -3.7602

Max Act: 1.2224. Min Act: -0.0001

Data Index: 1248943 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 3.7602. Min Range: -3.7602

Max Act: 1.4289. Min Act: -0.0001

Data Index: 129625 (C4 (Web Text))

Max Activating Token Index: 886