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

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

Neuron 4556 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: 4.6593. Min Range: -4.6593

Max Act: 4.6593. Min Act: -0.0000

Data Index: 1374542 (Python Code)

Max Activating Token Index: 854

Text #1

Max Range: 4.6593. Min Range: -4.6593

Max Act: 4.1420. Min Act: -0.0000

Data Index: 1502311 (Python Code)

Max Activating Token Index: 102

Text #2

Max Range: 4.6593. Min Range: -4.6593

Max Act: 3.8567. Min Act: -0.0000

Data Index: 1455477 (Python Code)

Max Activating Token Index: 620

Text #3

Max Range: 4.6593. Min Range: -4.6593

Max Act: 3.5842. Min Act: -0.0000

Data Index: 1444716 (Python Code)

Max Activating Token Index: 145

Text #4

Max Range: 4.6593. Min Range: -4.6593

Max Act: 3.5737. Min Act: -0.0000

Data Index: 1502894 (Python Code)

Max Activating Token Index: 997

Text #5

Max Range: 4.6593. Min Range: -4.6593

Max Act: 3.3772. Min Act: -0.0001

Data Index: 1376953 (Python Code)

Max Activating Token Index: 450

Text #6

Max Range: 4.6593. Min Range: -4.6593

Max Act: 3.0779. Min Act: -0.0000

Data Index: 1482777 (Python Code)

Max Activating Token Index: 486

Text #7

Max Range: 4.6593. Min Range: -4.6593

Max Act: 2.1996. Min Act: -0.0000

Data Index: 1571465 (Python Code)

Max Activating Token Index: 691

Text #8

Max Range: 4.6593. Min Range: -4.6593

Max Act: 2.5849. Min Act: -0.0000

Data Index: 1639031 (Python Code)

Max Activating Token Index: 737

Text #9

Max Range: 4.6593. Min Range: -4.6593

Max Act: 2.4628. Min Act: -0.0000

Data Index: 1562212 (Python Code)

Max Activating Token Index: 524

Text #10

Max Range: 4.6593. Min Range: -4.6593

Max Act: 2.3271. Min Act: -0.0000

Data Index: 1373820 (Python Code)

Max Activating Token Index: 593

Text #11

Max Range: 4.6593. Min Range: -4.6593

Max Act: 2.3300. Min Act: -0.0000

Data Index: 1414915 (Python Code)

Max Activating Token Index: 774

Text #12

Max Range: 4.6593. Min Range: -4.6593

Max Act: 2.4388. Min Act: -0.0000

Data Index: 1496333 (Python Code)

Max Activating Token Index: 877

Text #13

Max Range: 4.6593. Min Range: -4.6593

Max Act: 2.0388. Min Act: -0.0000

Data Index: 1376338 (Python Code)

Max Activating Token Index: 71

Text #14

Max Range: 4.6593. Min Range: -4.6593

Max Act: 2.4528. Min Act: -0.0001

Data Index: 1430041 (Python Code)

Max Activating Token Index: 329

Text #15

Max Range: 4.6593. Min Range: -4.6593

Max Act: 1.9986. Min Act: -0.0000

Data Index: 1368773 (Python Code)

Max Activating Token Index: 982

Text #16

Max Range: 4.6593. Min Range: -4.6593

Max Act: 2.2743. Min Act: -0.0000

Data Index: 1574025 (Python Code)

Max Activating Token Index: 255

Text #17

Max Range: 4.6593. Min Range: -4.6593

Max Act: 2.0156. Min Act: -0.0001

Data Index: 1441613 (Python Code)

Max Activating Token Index: 149

Text #18

Max Range: 4.6593. Min Range: -4.6593

Max Act: 2.0051. Min Act: -0.0000

Data Index: 1412183 (Python Code)

Max Activating Token Index: 295

Text #19

Max Range: 4.6593. Min Range: -4.6593

Max Act: 2.0777. Min Act: -0.0000

Data Index: 1426137 (Python Code)

Max Activating Token Index: 165