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

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

Neuron 1844 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0848. Min Range: -1.0848

Max Act: 1.0848. Min Act: -0.0001

Data Index: 1510100 (Python Code)

Max Activating Token Index: 872

Text #1

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.9420. Min Act: -0.0001

Data Index: 1456179 (Python Code)

Max Activating Token Index: 398

Text #2

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.8986. Min Act: -0.0001

Data Index: 1515942 (Python Code)

Max Activating Token Index: 320

Text #3

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.8518. Min Act: -0.0001

Data Index: 1607793 (Python Code)

Max Activating Token Index: 630

Text #4

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.8760. Min Act: -0.0001

Data Index: 1563481 (Python Code)

Max Activating Token Index: 632

Text #5

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.8186. Min Act: -0.0001

Data Index: 1527423 (Python Code)

Max Activating Token Index: 556

Text #6

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.7480. Min Act: -0.0001

Data Index: 1565324 (Python Code)

Max Activating Token Index: 740

Text #7

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.8211. Min Act: -0.0001

Data Index: 1588458 (Python Code)

Max Activating Token Index: 212

Text #8

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.8085. Min Act: -0.0001

Data Index: 1417277 (Python Code)

Max Activating Token Index: 688

Text #9

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.8406. Min Act: -0.0001

Data Index: 1462999 (Python Code)

Max Activating Token Index: 987

Text #10

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.8009. Min Act: -0.0001

Data Index: 1421483 (Python Code)

Max Activating Token Index: 545

Text #11

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.7975. Min Act: -0.0001

Data Index: 1513476 (Python Code)

Max Activating Token Index: 982

Text #12

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.7948. Min Act: -0.0001

Data Index: 1506825 (Python Code)

Max Activating Token Index: 847

Text #13

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.7640. Min Act: -0.0001

Data Index: 1375189 (Python Code)

Max Activating Token Index: 444

Text #14

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.7350. Min Act: -0.0001

Data Index: 1589277 (Python Code)

Max Activating Token Index: 363

Text #15

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.7842. Min Act: -0.0001

Data Index: 1563986 (Python Code)

Max Activating Token Index: 390

Text #16

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.7768. Min Act: -0.0001

Data Index: 1530858 (Python Code)

Max Activating Token Index: 428

Text #17

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.7628. Min Act: -0.0001

Data Index: 1508271 (Python Code)

Max Activating Token Index: 117

Text #18

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.8129. Min Act: -0.0001

Data Index: 1395914 (Python Code)

Max Activating Token Index: 465

Text #19

Max Range: 1.0848. Min Range: -1.0848

Max Act: 0.7957. Min Act: -0.0001

Data Index: 1653078 (Python Code)

Max Activating Token Index: 241