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

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

Neuron 3064 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.3554. Min Act: -0.0002

Data Index: 1605502 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.2233. Min Act: -0.0002

Data Index: 132387 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.1828. Min Act: -0.0002

Data Index: 370851 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.1400. Min Act: -0.0002

Data Index: 381079 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.1361. Min Act: -0.0002

Data Index: 20262 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.1287. Min Act: -0.0002

Data Index: 936847 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.1243. Min Act: -0.0002

Data Index: 1279975 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.1162. Min Act: -0.0002

Data Index: 727944 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.1098. Min Act: -0.0002

Data Index: 875485 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.1198. Min Act: -0.0002

Data Index: 334894 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.1175. Min Act: -0.0002

Data Index: 820327 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.1533. Min Act: -0.0002

Data Index: 1262345 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.0853. Min Act: -0.0002

Data Index: 1447325 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.0930. Min Act: -0.0002

Data Index: 873132 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.0881. Min Act: -0.0002

Data Index: 1247116 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.0958. Min Act: -0.0002

Data Index: 319602 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.0790. Min Act: -0.0002

Data Index: 293405 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.0841. Min Act: -0.0002

Data Index: 348299 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.0789. Min Act: -0.0002

Data Index: 1092078 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.3554. Min Range: -0.3554

Max Act: 0.0729. Min Act: -0.0002

Data Index: 1449128 (Python Code)

Max Activating Token Index: 1023