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

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

Neuron 3899 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2810. Min Range: -1.2810

Max Act: 1.2810. Min Act: -0.0001

Data Index: 1467507 (Python Code)

Max Activating Token Index: 272

Text #1

Max Range: 1.2810. Min Range: -1.2810

Max Act: 1.0907. Min Act: -0.0001

Data Index: 1396049 (Python Code)

Max Activating Token Index: 703

Text #2

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.9782. Min Act: -0.0000

Data Index: 1624480 (Python Code)

Max Activating Token Index: 987

Text #3

Max Range: 1.2810. Min Range: -1.2810

Max Act: 1.0374. Min Act: -0.0001

Data Index: 1619604 (Python Code)

Max Activating Token Index: 909

Text #4

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.9283. Min Act: -0.0001

Data Index: 1393627 (Python Code)

Max Activating Token Index: 593

Text #5

Max Range: 1.2810. Min Range: -1.2810

Max Act: 1.0766. Min Act: -0.0001

Data Index: 1438902 (Python Code)

Max Activating Token Index: 987

Text #6

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.9182. Min Act: -0.0001

Data Index: 1629115 (Python Code)

Max Activating Token Index: 568

Text #7

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.9216. Min Act: -0.0001

Data Index: 1473449 (Python Code)

Max Activating Token Index: 800

Text #8

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.8424. Min Act: -0.0001

Data Index: 1457521 (Python Code)

Max Activating Token Index: 1016

Text #9

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.8781. Min Act: -0.0001

Data Index: 1381432 (Python Code)

Max Activating Token Index: 430

Text #10

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.8528. Min Act: -0.0001

Data Index: 1577035 (Python Code)

Max Activating Token Index: 690

Text #11

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.8724. Min Act: -0.0001

Data Index: 1364771 (Python Code)

Max Activating Token Index: 620

Text #12

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.8785. Min Act: -0.0001

Data Index: 1440762 (Python Code)

Max Activating Token Index: 244

Text #13

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.8726. Min Act: -0.0001

Data Index: 1513125 (Python Code)

Max Activating Token Index: 747

Text #14

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.8641. Min Act: -0.0001

Data Index: 1369063 (Python Code)

Max Activating Token Index: 385

Text #15

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.8840. Min Act: -0.0001

Data Index: 1614108 (Python Code)

Max Activating Token Index: 201

Text #16

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.8494. Min Act: -0.0001

Data Index: 1523942 (Python Code)

Max Activating Token Index: 388

Text #17

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.8313. Min Act: -0.0001

Data Index: 1464210 (Python Code)

Max Activating Token Index: 244

Text #18

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.8632. Min Act: -0.0000

Data Index: 1617299 (Python Code)

Max Activating Token Index: 345

Text #19

Max Range: 1.2810. Min Range: -1.2810

Max Act: 0.8415. Min Act: -0.0001

Data Index: 1435856 (Python Code)

Max Activating Token Index: 397