Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4835 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9659. Min Range: -1.9659

Max Act: 1.9659. Min Act: -0.0000

Data Index: 1593068 (Python Code)

Max Activating Token Index: 12

Text #1

Max Range: 1.9659. Min Range: -1.9659

Max Act: 1.8144. Min Act: -0.0001

Data Index: 1478622 (Python Code)

Max Activating Token Index: 525

Text #2

Max Range: 1.9659. Min Range: -1.9659

Max Act: 1.7482. Min Act: -0.0000

Data Index: 1624834 (Python Code)

Max Activating Token Index: 276

Text #3

Max Range: 1.9659. Min Range: -1.9659

Max Act: 1.7251. Min Act: -0.0000

Data Index: 1505425 (Python Code)

Max Activating Token Index: 394

Text #4

Max Range: 1.9659. Min Range: -1.9659

Max Act: 1.6092. Min Act: -0.0000

Data Index: 1485845 (Python Code)

Max Activating Token Index: 10

Text #5

Max Range: 1.9659. Min Range: -1.9659

Max Act: 1.5630. Min Act: -0.0001

Data Index: 1416201 (Python Code)

Max Activating Token Index: 114

Text #6

Max Range: 1.9659. Min Range: -1.9659

Max Act: 1.6122. Min Act: -0.0000

Data Index: 1527616 (Python Code)

Max Activating Token Index: 70

Text #7

Max Range: 1.9659. Min Range: -1.9659

Max Act: 1.5142. Min Act: -0.0000

Data Index: 78540 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 1.9659. Min Range: -1.9659

Max Act: 1.6896. Min Act: -0.0001

Data Index: 1493970 (Python Code)

Max Activating Token Index: 552

Text #9

Max Range: 1.9659. Min Range: -1.9659

Max Act: 1.5031. Min Act: -0.0001

Data Index: 294975 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 1.9659. Min Range: -1.9659

Max Act: 1.5466. Min Act: -0.0000

Data Index: 1355803 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 1.9659. Min Range: -1.9659

Max Act: 1.5334. Min Act: -0.0000

Data Index: 1443845 (Python Code)

Max Activating Token Index: 499

Text #12

Max Range: 1.9659. Min Range: -1.9659

Max Act: 1.5618. Min Act: -0.0001

Data Index: 1622342 (Python Code)

Max Activating Token Index: 850

Text #13

Max Range: 1.9659. Min Range: -1.9659

Max Act: 1.5316. Min Act: -0.0001

Data Index: 1012127 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 1.9659. Min Range: -1.9659

Max Act: 1.5693. Min Act: -0.0000

Data Index: 1418149 (Python Code)

Max Activating Token Index: 498

Text #15

Max Range: 1.9659. Min Range: -1.9659

Max Act: 1.5314. Min Act: -0.0001

Data Index: 1513307 (Python Code)

Max Activating Token Index: 275

Text #16

Max Range: 1.9659. Min Range: -1.9659

Max Act: 1.5499. Min Act: -0.0000

Data Index: 1613266 (Python Code)

Max Activating Token Index: 917

Text #17

Max Range: 1.9659. Min Range: -1.9659

Max Act: 1.4906. Min Act: -0.0000

Data Index: 1576698 (Python Code)

Max Activating Token Index: 180

Text #18

Max Range: 1.9659. Min Range: -1.9659

Max Act: 1.4521. Min Act: -0.0000

Data Index: 1512369 (Python Code)

Max Activating Token Index: 64

Text #19

Max Range: 1.9659. Min Range: -1.9659

Max Act: 1.4903. Min Act: -0.0001

Data Index: 1507496 (Python Code)

Max Activating Token Index: 293