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

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

Neuron 1527 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.8917. Min Act: -0.0000

Data Index: 1463324 (Python Code)

Max Activating Token Index: 41

Text #1

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.9227. Min Act: -0.0000

Data Index: 1593259 (Python Code)

Max Activating Token Index: 44

Text #2

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.8844. Min Act: -0.0000

Data Index: 1627055 (Python Code)

Max Activating Token Index: 34

Text #3

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.8440. Min Act: -0.0000

Data Index: 1559191 (Python Code)

Max Activating Token Index: 57

Text #4

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.8649. Min Act: -0.0000

Data Index: 1584659 (Python Code)

Max Activating Token Index: 29

Text #5

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.8565. Min Act: -0.0000

Data Index: 1428997 (Python Code)

Max Activating Token Index: 41

Text #6

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.8263. Min Act: -0.0001

Data Index: 1360193 (Python Code)

Max Activating Token Index: 73

Text #7

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.8027. Min Act: -0.0000

Data Index: 1580447 (Python Code)

Max Activating Token Index: 18

Text #8

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.7916. Min Act: -0.0000

Data Index: 1457601 (Python Code)

Max Activating Token Index: 68

Text #9

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.7839. Min Act: -0.0000

Data Index: 1515244 (Python Code)

Max Activating Token Index: 90

Text #10

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.7380. Min Act: -0.0000

Data Index: 1539665 (Python Code)

Max Activating Token Index: 23

Text #11

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.7862. Min Act: -0.0000

Data Index: 1603150 (Python Code)

Max Activating Token Index: 166

Text #12

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.7543. Min Act: -0.0000

Data Index: 1518584 (Python Code)

Max Activating Token Index: 86

Text #13

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.7502. Min Act: -0.0000

Data Index: 1476462 (Python Code)

Max Activating Token Index: 50

Text #14

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.6903. Min Act: -0.0000

Data Index: 1580641 (Python Code)

Max Activating Token Index: 272

Text #15

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.7307. Min Act: -0.0000

Data Index: 1463207 (Python Code)

Max Activating Token Index: 66

Text #16

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.6884. Min Act: -0.0000

Data Index: 1629152 (Python Code)

Max Activating Token Index: 13

Text #17

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.7529. Min Act: -0.0000

Data Index: 1532045 (Python Code)

Max Activating Token Index: 109

Text #18

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.7076. Min Act: -0.0000

Data Index: 1394301 (Python Code)

Max Activating Token Index: 45

Text #19

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.7737. Min Act: -0.0000

Data Index: 1647374 (Python Code)

Max Activating Token Index: 81