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

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

Neuron 3044 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0242. Min Range: -1.0242

Max Act: 1.0242. Min Act: -0.0001

Data Index: 1580606 (Python Code)

Max Activating Token Index: 153

Text #1

Max Range: 1.0242. Min Range: -1.0242

Max Act: 1.0163. Min Act: -0.0001

Data Index: 1656294 (Python Code)

Max Activating Token Index: 742

Text #2

Max Range: 1.0242. Min Range: -1.0242

Max Act: 0.9506. Min Act: -0.0001

Data Index: 1546354 (Python Code)

Max Activating Token Index: 15

Text #3

Max Range: 1.0242. Min Range: -1.0242

Max Act: 0.8944. Min Act: -0.0001

Data Index: 1397803 (Python Code)

Max Activating Token Index: 630

Text #4

Max Range: 1.0242. Min Range: -1.0242

Max Act: 0.8826. Min Act: -0.0001

Data Index: 1642498 (Python Code)

Max Activating Token Index: 394

Text #5

Max Range: 1.0242. Min Range: -1.0242

Max Act: 0.8430. Min Act: -0.0001

Data Index: 1496539 (Python Code)

Max Activating Token Index: 95

Text #6

Max Range: 1.0242. Min Range: -1.0242

Max Act: 0.8781. Min Act: -0.0001

Data Index: 1592739 (Python Code)

Max Activating Token Index: 154

Text #7

Max Range: 1.0242. Min Range: -1.0242

Max Act: 0.8218. Min Act: -0.0001

Data Index: 1423030 (Python Code)

Max Activating Token Index: 2

Text #8

Max Range: 1.0242. Min Range: -1.0242

Max Act: 0.8218. Min Act: -0.0001

Data Index: 1590896 (Python Code)

Max Activating Token Index: 2

Text #9

Max Range: 1.0242. Min Range: -1.0242

Max Act: 0.7719. Min Act: -0.0001

Data Index: 1592051 (Python Code)

Max Activating Token Index: 209

Text #10

Max Range: 1.0242. Min Range: -1.0242

Max Act: 0.7765. Min Act: -0.0001

Data Index: 1458824 (Python Code)

Max Activating Token Index: 325

Text #11

Max Range: 1.0242. Min Range: -1.0242

Max Act: 0.7919. Min Act: -0.0001

Data Index: 1459312 (Python Code)

Max Activating Token Index: 233

Text #12

Max Range: 1.0242. Min Range: -1.0242

Max Act: 0.8353. Min Act: -0.0001

Data Index: 1367251 (Python Code)

Max Activating Token Index: 17

Text #13

Max Range: 1.0242. Min Range: -1.0242

Max Act: 0.8099. Min Act: -0.0001

Data Index: 1434512 (Python Code)

Max Activating Token Index: 237

Text #14

Max Range: 1.0242. Min Range: -1.0242

Max Act: 0.8215. Min Act: -0.0001

Data Index: 1429911 (Python Code)

Max Activating Token Index: 297

Text #15

Max Range: 1.0242. Min Range: -1.0242

Max Act: 0.8029. Min Act: -0.0001

Data Index: 1441274 (Python Code)

Max Activating Token Index: 854

Text #16

Max Range: 1.0242. Min Range: -1.0242

Max Act: 0.8490. Min Act: -0.0001

Data Index: 1648441 (Python Code)

Max Activating Token Index: 184

Text #17

Max Range: 1.0242. Min Range: -1.0242

Max Act: 0.7748. Min Act: -0.0001

Data Index: 1567497 (Python Code)

Max Activating Token Index: 11

Text #18

Max Range: 1.0242. Min Range: -1.0242

Max Act: 0.7748. Min Act: -0.0001

Data Index: 1571077 (Python Code)

Max Activating Token Index: 11

Text #19

Max Range: 1.0242. Min Range: -1.0242

Max Act: 0.7681. Min Act: -0.0001

Data Index: 916473 (C4 (Web Text))

Max Activating Token Index: 610