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

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

Neuron 1652 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1125. Min Range: -2.1125

Max Act: 2.0957. Min Act: -0.0000

Data Index: 1581377 (Python Code)

Max Activating Token Index: 691

Text #1

Max Range: 2.1125. Min Range: -2.1125

Max Act: 2.0318. Min Act: -0.0000

Data Index: 1424025 (Python Code)

Max Activating Token Index: 170

Text #2

Max Range: 2.1125. Min Range: -2.1125

Max Act: 2.0823. Min Act: -0.0000

Data Index: 1533629 (Python Code)

Max Activating Token Index: 116

Text #3

Max Range: 2.1125. Min Range: -2.1125

Max Act: 1.9712. Min Act: -0.0000

Data Index: 1392444 (Python Code)

Max Activating Token Index: 462

Text #4

Max Range: 2.1125. Min Range: -2.1125

Max Act: 2.1125. Min Act: -0.0000

Data Index: 1569765 (Python Code)

Max Activating Token Index: 840

Text #5

Max Range: 2.1125. Min Range: -2.1125

Max Act: 1.8791. Min Act: -0.0000

Data Index: 1598978 (Python Code)

Max Activating Token Index: 763

Text #6

Max Range: 2.1125. Min Range: -2.1125

Max Act: 1.9897. Min Act: -0.0000

Data Index: 1534409 (Python Code)

Max Activating Token Index: 937

Text #7

Max Range: 2.1125. Min Range: -2.1125

Max Act: 1.9534. Min Act: -0.0000

Data Index: 1411564 (Python Code)

Max Activating Token Index: 617

Text #8

Max Range: 2.1125. Min Range: -2.1125

Max Act: 1.8598. Min Act: -0.0000

Data Index: 1643415 (Python Code)

Max Activating Token Index: 564

Text #9

Max Range: 2.1125. Min Range: -2.1125

Max Act: 1.9247. Min Act: -0.0000

Data Index: 1591818 (Python Code)

Max Activating Token Index: 219

Text #10

Max Range: 2.1125. Min Range: -2.1125

Max Act: 1.8887. Min Act: -0.0000

Data Index: 1362252 (Python Code)

Max Activating Token Index: 893

Text #11

Max Range: 2.1125. Min Range: -2.1125

Max Act: 1.7390. Min Act: -0.0000

Data Index: 1419749 (Python Code)

Max Activating Token Index: 432

Text #12

Max Range: 2.1125. Min Range: -2.1125

Max Act: 1.5829. Min Act: -0.0000

Data Index: 1399545 (Python Code)

Max Activating Token Index: 915

Text #13

Max Range: 2.1125. Min Range: -2.1125

Max Act: 1.8883. Min Act: -0.0000

Data Index: 1518442 (Python Code)

Max Activating Token Index: 27

Text #14

Max Range: 2.1125. Min Range: -2.1125

Max Act: 1.7536. Min Act: -0.0000

Data Index: 1547508 (Python Code)

Max Activating Token Index: 50

Text #15

Max Range: 2.1125. Min Range: -2.1125

Max Act: 1.7585. Min Act: -0.0000

Data Index: 1544116 (Python Code)

Max Activating Token Index: 473

Text #16

Max Range: 2.1125. Min Range: -2.1125

Max Act: 1.6373. Min Act: -0.0000

Data Index: 1632159 (Python Code)

Max Activating Token Index: 918

Text #17

Max Range: 2.1125. Min Range: -2.1125

Max Act: 1.6592. Min Act: -0.0001

Data Index: 1650592 (Python Code)

Max Activating Token Index: 999

Text #18

Max Range: 2.1125. Min Range: -2.1125

Max Act: 1.6791. Min Act: -0.0000

Data Index: 1436705 (Python Code)

Max Activating Token Index: 355

Text #19

Max Range: 2.1125. Min Range: -2.1125

Max Act: 1.6795. Min Act: -0.0000

Data Index: 1493238 (Python Code)

Max Activating Token Index: 563