Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1436 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2212. Min Range: -1.2212

Max Act: 1.1712. Min Act: -0.0001

Data Index: 1595649 (Python Code)

Max Activating Token Index: 632

Text #1

Max Range: 1.2212. Min Range: -1.2212

Max Act: 1.2212. Min Act: -0.0001

Data Index: 1377034 (Python Code)

Max Activating Token Index: 991

Text #2

Max Range: 1.2212. Min Range: -1.2212

Max Act: 1.0036. Min Act: -0.0001

Data Index: 1402032 (Python Code)

Max Activating Token Index: 279

Text #3

Max Range: 1.2212. Min Range: -1.2212

Max Act: 1.0631. Min Act: -0.0001

Data Index: 1410539 (Python Code)

Max Activating Token Index: 629

Text #4

Max Range: 1.2212. Min Range: -1.2212

Max Act: 1.0222. Min Act: -0.0001

Data Index: 1369965 (Python Code)

Max Activating Token Index: 251

Text #5

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.9851. Min Act: -0.0001

Data Index: 1609530 (Python Code)

Max Activating Token Index: 45

Text #6

Max Range: 1.2212. Min Range: -1.2212

Max Act: 1.0079. Min Act: -0.0001

Data Index: 1385966 (Python Code)

Max Activating Token Index: 41

Text #7

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.9388. Min Act: -0.0001

Data Index: 1644826 (Python Code)

Max Activating Token Index: 926

Text #8

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.9181. Min Act: -0.0001

Data Index: 1441807 (Python Code)

Max Activating Token Index: 662

Text #9

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.9099. Min Act: -0.0001

Data Index: 1475793 (Python Code)

Max Activating Token Index: 977

Text #10

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.9452. Min Act: -0.0001

Data Index: 1411766 (Python Code)

Max Activating Token Index: 899

Text #11

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.9251. Min Act: -0.0001

Data Index: 1382633 (Python Code)

Max Activating Token Index: 407

Text #12

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.9304. Min Act: -0.0001

Data Index: 1484053 (Python Code)

Max Activating Token Index: 941

Text #13

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.8364. Min Act: -0.0001

Data Index: 1564459 (Python Code)

Max Activating Token Index: 267

Text #14

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.8804. Min Act: -0.0001

Data Index: 1510662 (Python Code)

Max Activating Token Index: 647

Text #15

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.8964. Min Act: -0.0001

Data Index: 1488952 (Python Code)

Max Activating Token Index: 640

Text #16

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.8581. Min Act: -0.0001

Data Index: 1587063 (Python Code)

Max Activating Token Index: 522

Text #17

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.8729. Min Act: -0.0001

Data Index: 1403963 (Python Code)

Max Activating Token Index: 420

Text #18

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.8501. Min Act: -0.0001

Data Index: 1635541 (Python Code)

Max Activating Token Index: 902

Text #19

Max Range: 1.2212. Min Range: -1.2212

Max Act: 0.8028. Min Act: -0.0001

Data Index: 1408124 (Python Code)

Max Activating Token Index: 125