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

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

Neuron 2706 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2644. Min Range: -2.2644

Max Act: 2.2644. Min Act: -0.0000

Data Index: 1571845 (Python Code)

Max Activating Token Index: 922

Text #1

Max Range: 2.2644. Min Range: -2.2644

Max Act: 1.3591. Min Act: -0.0000

Data Index: 1369574 (Python Code)

Max Activating Token Index: 628

Text #2

Max Range: 2.2644. Min Range: -2.2644

Max Act: 1.3517. Min Act: -0.0000

Data Index: 92174 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 2.2644. Min Range: -2.2644

Max Act: 1.3922. Min Act: -0.0000

Data Index: 1550720 (Python Code)

Max Activating Token Index: 693

Text #4

Max Range: 2.2644. Min Range: -2.2644

Max Act: 1.3379. Min Act: -0.0000

Data Index: 1450612 (Python Code)

Max Activating Token Index: 8

Text #5

Max Range: 2.2644. Min Range: -2.2644

Max Act: 1.2407. Min Act: -0.0000

Data Index: 1228901 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 2.2644. Min Range: -2.2644

Max Act: 1.2266. Min Act: -0.0000

Data Index: 994299 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 2.2644. Min Range: -2.2644

Max Act: 1.3082. Min Act: -0.0000

Data Index: 1495387 (Python Code)

Max Activating Token Index: 671

Text #8

Max Range: 2.2644. Min Range: -2.2644

Max Act: 1.2555. Min Act: -0.0000

Data Index: 1539733 (Python Code)

Max Activating Token Index: 174

Text #9

Max Range: 2.2644. Min Range: -2.2644

Max Act: 1.2431. Min Act: -0.0000

Data Index: 1424696 (Python Code)

Max Activating Token Index: 504

Text #10

Max Range: 2.2644. Min Range: -2.2644

Max Act: 1.1860. Min Act: -0.0000

Data Index: 1539521 (Python Code)

Max Activating Token Index: 866

Text #11

Max Range: 2.2644. Min Range: -2.2644

Max Act: 1.2316. Min Act: -0.0000

Data Index: 1639093 (Python Code)

Max Activating Token Index: 452

Text #12

Max Range: 2.2644. Min Range: -2.2644

Max Act: 1.2705. Min Act: -0.0000

Data Index: 1244853 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 2.2644. Min Range: -2.2644

Max Act: 1.1479. Min Act: -0.0000

Data Index: 1636235 (Python Code)

Max Activating Token Index: 752

Text #14

Max Range: 2.2644. Min Range: -2.2644

Max Act: 1.2182. Min Act: -0.0000

Data Index: 1558907 (Python Code)

Max Activating Token Index: 502

Text #15

Max Range: 2.2644. Min Range: -2.2644

Max Act: 1.2676. Min Act: -0.0000

Data Index: 1453191 (Python Code)

Max Activating Token Index: 11

Text #16

Max Range: 2.2644. Min Range: -2.2644

Max Act: 1.2276. Min Act: -0.0000

Data Index: 1380856 (Python Code)

Max Activating Token Index: 924

Text #17

Max Range: 2.2644. Min Range: -2.2644

Max Act: 1.2438. Min Act: -0.0000

Data Index: 1642045 (Python Code)

Max Activating Token Index: 279

Text #18

Max Range: 2.2644. Min Range: -2.2644

Max Act: 1.1184. Min Act: -0.0000

Data Index: 1515573 (Python Code)

Max Activating Token Index: 962

Text #19

Max Range: 2.2644. Min Range: -2.2644

Max Act: 1.0748. Min Act: -0.0000

Data Index: 1656144 (Python Code)

Max Activating Token Index: 823