Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2782 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0943. Min Range: -2.0943

Max Act: 2.0943. Min Act: -0.0000

Data Index: 1546279 (Python Code)

Max Activating Token Index: 609

Text #1

Max Range: 2.0943. Min Range: -2.0943

Max Act: 2.0318. Min Act: -0.0000

Data Index: 1369973 (Python Code)

Max Activating Token Index: 13

Text #2

Max Range: 2.0943. Min Range: -2.0943

Max Act: 2.0246. Min Act: -0.0000

Data Index: 1455501 (Python Code)

Max Activating Token Index: 10

Text #3

Max Range: 2.0943. Min Range: -2.0943

Max Act: 1.9016. Min Act: -0.0000

Data Index: 1428155 (Python Code)

Max Activating Token Index: 961

Text #4

Max Range: 2.0943. Min Range: -2.0943

Max Act: 1.9003. Min Act: -0.0000

Data Index: 1620083 (Python Code)

Max Activating Token Index: 977

Text #5

Max Range: 2.0943. Min Range: -2.0943

Max Act: 1.8585. Min Act: -0.0000

Data Index: 1544232 (Python Code)

Max Activating Token Index: 287

Text #6

Max Range: 2.0943. Min Range: -2.0943

Max Act: 1.8331. Min Act: -0.0000

Data Index: 1459308 (Python Code)

Max Activating Token Index: 12

Text #7

Max Range: 2.0943. Min Range: -2.0943

Max Act: 1.8226. Min Act: -0.0000

Data Index: 1362513 (Python Code)

Max Activating Token Index: 83

Text #8

Max Range: 2.0943. Min Range: -2.0943

Max Act: 1.7891. Min Act: -0.0000

Data Index: 1525958 (Python Code)

Max Activating Token Index: 762

Text #9

Max Range: 2.0943. Min Range: -2.0943

Max Act: 1.7728. Min Act: -0.0000

Data Index: 1364542 (Python Code)

Max Activating Token Index: 982

Text #10

Max Range: 2.0943. Min Range: -2.0943

Max Act: 1.7454. Min Act: -0.0000

Data Index: 1613535 (Python Code)

Max Activating Token Index: 780

Text #11

Max Range: 2.0943. Min Range: -2.0943

Max Act: 1.8411. Min Act: -0.0000

Data Index: 1495806 (Python Code)

Max Activating Token Index: 223

Text #12

Max Range: 2.0943. Min Range: -2.0943

Max Act: 1.7467. Min Act: -0.0000

Data Index: 1544115 (Python Code)

Max Activating Token Index: 14

Text #13

Max Range: 2.0943. Min Range: -2.0943

Max Act: 1.5969. Min Act: -0.0000

Data Index: 1359976 (Python Code)

Max Activating Token Index: 11

Text #14

Max Range: 2.0943. Min Range: -2.0943

Max Act: 1.6946. Min Act: -0.0000

Data Index: 1502005 (Python Code)

Max Activating Token Index: 58

Text #15

Max Range: 2.0943. Min Range: -2.0943

Max Act: 1.5877. Min Act: -0.0000

Data Index: 1547167 (Python Code)

Max Activating Token Index: 301

Text #16

Max Range: 2.0943. Min Range: -2.0943

Max Act: 1.6770. Min Act: -0.0000

Data Index: 1540223 (Python Code)

Max Activating Token Index: 610

Text #17

Max Range: 2.0943. Min Range: -2.0943

Max Act: 1.6569. Min Act: -0.0000

Data Index: 1568407 (Python Code)

Max Activating Token Index: 15

Text #18

Max Range: 2.0943. Min Range: -2.0943

Max Act: 1.7729. Min Act: -0.0000

Data Index: 1368296 (Python Code)

Max Activating Token Index: 347

Text #19

Max Range: 2.0943. Min Range: -2.0943

Max Act: 1.6697. Min Act: -0.0000

Data Index: 1507141 (Python Code)

Max Activating Token Index: 332