Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3339 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.4512. Min Act: -0.0000

Data Index: 1451737 (Python Code)

Max Activating Token Index: 42

Text #1

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.4112. Min Act: -0.0000

Data Index: 1603464 (Python Code)

Max Activating Token Index: 139

Text #2

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3915. Min Act: -0.0000

Data Index: 1440691 (Python Code)

Max Activating Token Index: 33

Text #3

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3968. Min Act: -0.0001

Data Index: 1657101 (Python Code)

Max Activating Token Index: 86

Text #4

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3791. Min Act: -0.0000

Data Index: 1561118 (Python Code)

Max Activating Token Index: 909

Text #5

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3634. Min Act: -0.0000

Data Index: 1577574 (Python Code)

Max Activating Token Index: 53

Text #6

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3587. Min Act: -0.0000

Data Index: 1526398 (Python Code)

Max Activating Token Index: 45

Text #7

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3737. Min Act: -0.0000

Data Index: 1501117 (Python Code)

Max Activating Token Index: 64

Text #8

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3585. Min Act: -0.0000

Data Index: 1497788 (Python Code)

Max Activating Token Index: 17

Text #9

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3433. Min Act: -0.0000

Data Index: 1602448 (Python Code)

Max Activating Token Index: 29

Text #10

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3511. Min Act: -0.0000

Data Index: 1466533 (Python Code)

Max Activating Token Index: 162

Text #11

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3466. Min Act: -0.0001

Data Index: 1627403 (Python Code)

Max Activating Token Index: 23

Text #12

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3035. Min Act: -0.0001

Data Index: 1498023 (Python Code)

Max Activating Token Index: 387

Text #13

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3212. Min Act: -0.0001

Data Index: 1551994 (Python Code)

Max Activating Token Index: 21

Text #14

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3182. Min Act: -0.0000

Data Index: 1595849 (Python Code)

Max Activating Token Index: 323

Text #15

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3292. Min Act: -0.0001

Data Index: 1516676 (Python Code)

Max Activating Token Index: 106

Text #16

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3058. Min Act: -0.0000

Data Index: 1624978 (Python Code)

Max Activating Token Index: 883

Text #17

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.2898. Min Act: -0.0000

Data Index: 1611574 (Python Code)

Max Activating Token Index: 301

Text #18

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3184. Min Act: -0.0001

Data Index: 1544331 (Python Code)

Max Activating Token Index: 950

Text #19

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.2949. Min Act: -0.0000

Data Index: 1534546 (Python Code)

Max Activating Token Index: 189