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

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

Neuron 1450 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: 1.3341. Min Range: -1.3341

Max Act: 1.3341. Min Act: -0.0001

Data Index: 1374921 (Python Code)

Max Activating Token Index: 281

Text #1

Max Range: 1.3341. Min Range: -1.3341

Max Act: 1.1918. Min Act: -0.0001

Data Index: 1409573 (Python Code)

Max Activating Token Index: 92

Text #2

Max Range: 1.3341. Min Range: -1.3341

Max Act: 1.2043. Min Act: -0.0001

Data Index: 1449005 (Python Code)

Max Activating Token Index: 158

Text #3

Max Range: 1.3341. Min Range: -1.3341

Max Act: 1.1911. Min Act: -0.0001

Data Index: 1611887 (Python Code)

Max Activating Token Index: 121

Text #4

Max Range: 1.3341. Min Range: -1.3341

Max Act: 1.2054. Min Act: -0.0001

Data Index: 1506525 (Python Code)

Max Activating Token Index: 195

Text #5

Max Range: 1.3341. Min Range: -1.3341

Max Act: 1.1917. Min Act: -0.0001

Data Index: 1573119 (Python Code)

Max Activating Token Index: 919

Text #6

Max Range: 1.3341. Min Range: -1.3341

Max Act: 1.1558. Min Act: -0.0001

Data Index: 1656321 (Python Code)

Max Activating Token Index: 792

Text #7

Max Range: 1.3341. Min Range: -1.3341

Max Act: 1.1487. Min Act: -0.0001

Data Index: 1361307 (Python Code)

Max Activating Token Index: 828

Text #8

Max Range: 1.3341. Min Range: -1.3341

Max Act: 1.0655. Min Act: -0.0001

Data Index: 1637534 (Python Code)

Max Activating Token Index: 26

Text #9

Max Range: 1.3341. Min Range: -1.3341

Max Act: 1.1436. Min Act: -0.0001

Data Index: 1554887 (Python Code)

Max Activating Token Index: 563

Text #10

Max Range: 1.3341. Min Range: -1.3341

Max Act: 1.0384. Min Act: -0.0001

Data Index: 1650942 (Python Code)

Max Activating Token Index: 133

Text #11

Max Range: 1.3341. Min Range: -1.3341

Max Act: 1.0434. Min Act: -0.0001

Data Index: 1604587 (Python Code)

Max Activating Token Index: 758

Text #12

Max Range: 1.3341. Min Range: -1.3341

Max Act: 1.0318. Min Act: -0.0001

Data Index: 1559110 (Python Code)

Max Activating Token Index: 15

Text #13

Max Range: 1.3341. Min Range: -1.3341

Max Act: 1.1295. Min Act: -0.0001

Data Index: 1582915 (Python Code)

Max Activating Token Index: 322

Text #14

Max Range: 1.3341. Min Range: -1.3341

Max Act: 0.9924. Min Act: -0.0001

Data Index: 1627826 (Python Code)

Max Activating Token Index: 532

Text #15

Max Range: 1.3341. Min Range: -1.3341

Max Act: 1.0017. Min Act: -0.0001

Data Index: 1416901 (Python Code)

Max Activating Token Index: 193

Text #16

Max Range: 1.3341. Min Range: -1.3341

Max Act: 1.1081. Min Act: -0.0001

Data Index: 1452417 (Python Code)

Max Activating Token Index: 507

Text #17

Max Range: 1.3341. Min Range: -1.3341

Max Act: 0.9983. Min Act: -0.0001

Data Index: 1551084 (Python Code)

Max Activating Token Index: 118

Text #18

Max Range: 1.3341. Min Range: -1.3341

Max Act: 1.0729. Min Act: -0.0001

Data Index: 1537246 (Python Code)

Max Activating Token Index: 71

Text #19

Max Range: 1.3341. Min Range: -1.3341

Max Act: 1.1015. Min Act: -0.0001

Data Index: 1429223 (Python Code)

Max Activating Token Index: 722