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

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

Neuron 671 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2543. Min Range: -5.2543

Max Act: 5.2543. Min Act: -0.0000

Data Index: 1446066 (Python Code)

Max Activating Token Index: 98

Text #1

Max Range: 5.2543. Min Range: -5.2543

Max Act: 4.8015. Min Act: -0.0000

Data Index: 1396485 (Python Code)

Max Activating Token Index: 643

Text #2

Max Range: 5.2543. Min Range: -5.2543

Max Act: 4.4119. Min Act: -0.0000

Data Index: 1550382 (Python Code)

Max Activating Token Index: 334

Text #3

Max Range: 5.2543. Min Range: -5.2543

Max Act: 3.9045. Min Act: -0.0000

Data Index: 1453318 (Python Code)

Max Activating Token Index: 35

Text #4

Max Range: 5.2543. Min Range: -5.2543

Max Act: 3.5813. Min Act: -0.0000

Data Index: 1500614 (Python Code)

Max Activating Token Index: 124

Text #5

Max Range: 5.2543. Min Range: -5.2543

Max Act: 3.7188. Min Act: -0.0000

Data Index: 1427809 (Python Code)

Max Activating Token Index: 126

Text #6

Max Range: 5.2543. Min Range: -5.2543

Max Act: 3.6548. Min Act: -0.0000

Data Index: 1414122 (Python Code)

Max Activating Token Index: 467

Text #7

Max Range: 5.2543. Min Range: -5.2543

Max Act: 3.8010. Min Act: -0.0000

Data Index: 1548653 (Python Code)

Max Activating Token Index: 143

Text #8

Max Range: 5.2543. Min Range: -5.2543

Max Act: 3.5325. Min Act: -0.0000

Data Index: 1486388 (Python Code)

Max Activating Token Index: 534

Text #9

Max Range: 5.2543. Min Range: -5.2543

Max Act: 3.3200. Min Act: -0.0000

Data Index: 1394293 (Python Code)

Max Activating Token Index: 39

Text #10

Max Range: 5.2543. Min Range: -5.2543

Max Act: 3.2440. Min Act: -0.0000

Data Index: 1394058 (Python Code)

Max Activating Token Index: 111

Text #11

Max Range: 5.2543. Min Range: -5.2543

Max Act: 3.1493. Min Act: -0.0000

Data Index: 1450259 (Python Code)

Max Activating Token Index: 1008

Text #12

Max Range: 5.2543. Min Range: -5.2543

Max Act: 3.2658. Min Act: -0.0000

Data Index: 1582101 (Python Code)

Max Activating Token Index: 585

Text #13

Max Range: 5.2543. Min Range: -5.2543

Max Act: 3.0552. Min Act: -0.0000

Data Index: 1393755 (Python Code)

Max Activating Token Index: 21

Text #14

Max Range: 5.2543. Min Range: -5.2543

Max Act: 3.4303. Min Act: -0.0000

Data Index: 1511768 (Python Code)

Max Activating Token Index: 976

Text #15

Max Range: 5.2543. Min Range: -5.2543

Max Act: 3.1068. Min Act: -0.0000

Data Index: 1513963 (Python Code)

Max Activating Token Index: 100

Text #16

Max Range: 5.2543. Min Range: -5.2543

Max Act: 3.0420. Min Act: -0.0000

Data Index: 1520637 (Python Code)

Max Activating Token Index: 736

Text #17

Max Range: 5.2543. Min Range: -5.2543

Max Act: 3.1439. Min Act: -0.0000

Data Index: 1456325 (Python Code)

Max Activating Token Index: 150

Text #18

Max Range: 5.2543. Min Range: -5.2543

Max Act: 3.1466. Min Act: -0.0000

Data Index: 1465324 (Python Code)

Max Activating Token Index: 150

Text #19

Max Range: 5.2543. Min Range: -5.2543

Max Act: 2.9747. Min Act: -0.0000

Data Index: 1454109 (Python Code)

Max Activating Token Index: 421