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

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

Neuron 2990 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3882. Min Range: -1.3882

Max Act: 1.3882. Min Act: -0.0000

Data Index: 1495949 (Python Code)

Max Activating Token Index: 971

Text #1

Max Range: 1.3882. Min Range: -1.3882

Max Act: 0.9119. Min Act: -0.0000

Data Index: 1487835 (Python Code)

Max Activating Token Index: 667

Text #2

Max Range: 1.3882. Min Range: -1.3882

Max Act: 0.9773. Min Act: -0.0000

Data Index: 1590416 (Python Code)

Max Activating Token Index: 570

Text #3

Max Range: 1.3882. Min Range: -1.3882

Max Act: 0.9386. Min Act: -0.0000

Data Index: 1537218 (Python Code)

Max Activating Token Index: 515

Text #4

Max Range: 1.3882. Min Range: -1.3882

Max Act: 0.9213. Min Act: -0.0000

Data Index: 1517206 (Python Code)

Max Activating Token Index: 610

Text #5

Max Range: 1.3882. Min Range: -1.3882

Max Act: 0.9489. Min Act: -0.0000

Data Index: 1411439 (Python Code)

Max Activating Token Index: 568

Text #6

Max Range: 1.3882. Min Range: -1.3882

Max Act: 0.8529. Min Act: 0.0000

Data Index: 1446962 (Python Code)

Max Activating Token Index: 940

Text #7

Max Range: 1.3882. Min Range: -1.3882

Max Act: 0.8387. Min Act: -0.0000

Data Index: 1526615 (Python Code)

Max Activating Token Index: 350

Text #8

Max Range: 1.3882. Min Range: -1.3882

Max Act: 0.8367. Min Act: -0.0000

Data Index: 1379537 (Python Code)

Max Activating Token Index: 750

Text #9

Max Range: 1.3882. Min Range: -1.3882

Max Act: 0.8008. Min Act: -0.0000

Data Index: 1376043 (Python Code)

Max Activating Token Index: 56

Text #10

Max Range: 1.3882. Min Range: -1.3882

Max Act: 0.7697. Min Act: -0.0000

Data Index: 1631747 (Python Code)

Max Activating Token Index: 237

Text #11

Max Range: 1.3882. Min Range: -1.3882

Max Act: 0.8164. Min Act: 0.0000

Data Index: 1479796 (Python Code)

Max Activating Token Index: 257

Text #12

Max Range: 1.3882. Min Range: -1.3882

Max Act: 0.8264. Min Act: -0.0000

Data Index: 1476218 (Python Code)

Max Activating Token Index: 100

Text #13

Max Range: 1.3882. Min Range: -1.3882

Max Act: 0.8109. Min Act: -0.0000

Data Index: 1493264 (Python Code)

Max Activating Token Index: 354

Text #14

Max Range: 1.3882. Min Range: -1.3882

Max Act: 0.7432. Min Act: -0.0000

Data Index: 1407695 (Python Code)

Max Activating Token Index: 537

Text #15

Max Range: 1.3882. Min Range: -1.3882

Max Act: 0.7050. Min Act: 0.0000

Data Index: 1577446 (Python Code)

Max Activating Token Index: 693

Text #16

Max Range: 1.3882. Min Range: -1.3882

Max Act: 0.7131. Min Act: -0.0000

Data Index: 1607965 (Python Code)

Max Activating Token Index: 639

Text #17

Max Range: 1.3882. Min Range: -1.3882

Max Act: 0.7577. Min Act: -0.0000

Data Index: 1513603 (Python Code)

Max Activating Token Index: 679

Text #18

Max Range: 1.3882. Min Range: -1.3882

Max Act: 0.7070. Min Act: -0.0000

Data Index: 1582745 (Python Code)

Max Activating Token Index: 42

Text #19

Max Range: 1.3882. Min Range: -1.3882

Max Act: 0.6818. Min Act: -0.0000

Data Index: 1391823 (Python Code)

Max Activating Token Index: 238