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

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

Neuron 3865 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8575. Min Range: -1.8575

Max Act: 1.8575. Min Act: -0.0000

Data Index: 1378604 (Python Code)

Max Activating Token Index: 448

Text #1

Max Range: 1.8575. Min Range: -1.8575

Max Act: 1.6465. Min Act: -0.0000

Data Index: 1475458 (Python Code)

Max Activating Token Index: 397

Text #2

Max Range: 1.8575. Min Range: -1.8575

Max Act: 1.6159. Min Act: -0.0000

Data Index: 1391289 (Python Code)

Max Activating Token Index: 190

Text #3

Max Range: 1.8575. Min Range: -1.8575

Max Act: 1.5245. Min Act: -0.0000

Data Index: 1463250 (Python Code)

Max Activating Token Index: 593

Text #4

Max Range: 1.8575. Min Range: -1.8575

Max Act: 1.5844. Min Act: -0.0000

Data Index: 1609487 (Python Code)

Max Activating Token Index: 141

Text #5

Max Range: 1.8575. Min Range: -1.8575

Max Act: 1.4998. Min Act: -0.0000

Data Index: 1483023 (Python Code)

Max Activating Token Index: 948

Text #6

Max Range: 1.8575. Min Range: -1.8575

Max Act: 1.5340. Min Act: -0.0000

Data Index: 1399576 (Python Code)

Max Activating Token Index: 897

Text #7

Max Range: 1.8575. Min Range: -1.8575

Max Act: 1.6371. Min Act: -0.0000

Data Index: 1578673 (Python Code)

Max Activating Token Index: 271

Text #8

Max Range: 1.8575. Min Range: -1.8575

Max Act: 1.5278. Min Act: -0.0000

Data Index: 1365940 (Python Code)

Max Activating Token Index: 448

Text #9

Max Range: 1.8575. Min Range: -1.8575

Max Act: 1.4308. Min Act: -0.0000

Data Index: 1394011 (Python Code)

Max Activating Token Index: 915

Text #10

Max Range: 1.8575. Min Range: -1.8575

Max Act: 1.5886. Min Act: -0.0000

Data Index: 1424522 (Python Code)

Max Activating Token Index: 947

Text #11

Max Range: 1.8575. Min Range: -1.8575

Max Act: 1.5044. Min Act: -0.0000

Data Index: 1362190 (Python Code)

Max Activating Token Index: 751

Text #12

Max Range: 1.8575. Min Range: -1.8575

Max Act: 1.5875. Min Act: -0.0000

Data Index: 1537332 (Python Code)

Max Activating Token Index: 891

Text #13

Max Range: 1.8575. Min Range: -1.8575

Max Act: 1.4700. Min Act: -0.0000

Data Index: 1480099 (Python Code)

Max Activating Token Index: 115

Text #14

Max Range: 1.8575. Min Range: -1.8575

Max Act: 1.5413. Min Act: -0.0000

Data Index: 1516594 (Python Code)

Max Activating Token Index: 202

Text #15

Max Range: 1.8575. Min Range: -1.8575

Max Act: 1.3593. Min Act: -0.0000

Data Index: 1533341 (Python Code)

Max Activating Token Index: 550

Text #16

Max Range: 1.8575. Min Range: -1.8575

Max Act: 1.4360. Min Act: -0.0000

Data Index: 1483619 (Python Code)

Max Activating Token Index: 191

Text #17

Max Range: 1.8575. Min Range: -1.8575

Max Act: 1.4375. Min Act: -0.0000

Data Index: 1377030 (Python Code)

Max Activating Token Index: 63

Text #18

Max Range: 1.8575. Min Range: -1.8575

Max Act: 1.4322. Min Act: -0.0000

Data Index: 1568719 (Python Code)

Max Activating Token Index: 831

Text #19

Max Range: 1.8575. Min Range: -1.8575

Max Act: 1.3321. Min Act: -0.0000

Data Index: 1546882 (Python Code)

Max Activating Token Index: 181