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

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

Neuron 4849 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1052. Min Range: -1.1052

Max Act: 1.1052. Min Act: -0.0000

Data Index: 1254740 (C4 (Web Text))

Max Activating Token Index: 305

Text #1

Max Range: 1.1052. Min Range: -1.1052

Max Act: 1.0389. Min Act: -0.0000

Data Index: 860981 (C4 (Web Text))

Max Activating Token Index: 507

Text #2

Max Range: 1.1052. Min Range: -1.1052

Max Act: 1.0568. Min Act: 0.0000

Data Index: 363122 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 1.1052. Min Range: -1.1052

Max Act: 1.0839. Min Act: -0.0000

Data Index: 1486920 (Python Code)

Max Activating Token Index: 81

Text #4

Max Range: 1.1052. Min Range: -1.1052

Max Act: 1.0460. Min Act: -0.0000

Data Index: 690169 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 1.1052. Min Range: -1.1052

Max Act: 1.0838. Min Act: -0.0000

Data Index: 1576053 (Python Code)

Max Activating Token Index: 667

Text #6

Max Range: 1.1052. Min Range: -1.1052

Max Act: 0.9787. Min Act: -0.0000

Data Index: 1365915 (Python Code)

Max Activating Token Index: 34

Text #7

Max Range: 1.1052. Min Range: -1.1052

Max Act: 1.0586. Min Act: -0.0000

Data Index: 705919 (C4 (Web Text))

Max Activating Token Index: 487

Text #8

Max Range: 1.1052. Min Range: -1.1052

Max Act: 0.9543. Min Act: -0.0000

Data Index: 388055 (C4 (Web Text))

Max Activating Token Index: 234

Text #9

Max Range: 1.1052. Min Range: -1.1052

Max Act: 0.8942. Min Act: -0.0000

Data Index: 1638547 (Python Code)

Max Activating Token Index: 94

Text #10

Max Range: 1.1052. Min Range: -1.1052

Max Act: 0.8919. Min Act: -0.0000

Data Index: 1581845 (Python Code)

Max Activating Token Index: 469

Text #11

Max Range: 1.1052. Min Range: -1.1052

Max Act: 0.8142. Min Act: -0.0000

Data Index: 1428262 (Python Code)

Max Activating Token Index: 789

Text #12

Max Range: 1.1052. Min Range: -1.1052

Max Act: 0.6392. Min Act: -0.0000

Data Index: 1209747 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 1.1052. Min Range: -1.1052

Max Act: 0.8613. Min Act: -0.0000

Data Index: 1484146 (Python Code)

Max Activating Token Index: 568

Text #14

Max Range: 1.1052. Min Range: -1.1052

Max Act: 0.8607. Min Act: -0.0000

Data Index: 1409748 (Python Code)

Max Activating Token Index: 641

Text #15

Max Range: 1.1052. Min Range: -1.1052

Max Act: 0.8044. Min Act: -0.0000

Data Index: 1097108 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 1.1052. Min Range: -1.1052

Max Act: 0.8510. Min Act: -0.0000

Data Index: 1561532 (Python Code)

Max Activating Token Index: 973

Text #17

Max Range: 1.1052. Min Range: -1.1052

Max Act: 0.8476. Min Act: -0.0000

Data Index: 1377077 (Python Code)

Max Activating Token Index: 155

Text #18

Max Range: 1.1052. Min Range: -1.1052

Max Act: 0.8608. Min Act: -0.0000

Data Index: 329479 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 1.1052. Min Range: -1.1052

Max Act: 0.8033. Min Act: -0.0000

Data Index: 806031 (C4 (Web Text))

Max Activating Token Index: 678