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

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

Neuron 4596 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.7020. Min Act: -0.0000

Data Index: 854004 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.7158. Min Act: -0.0000

Data Index: 1326335 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.7048. Min Act: -0.0000

Data Index: 750544 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.7052. Min Act: -0.0000

Data Index: 186464 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.6517. Min Act: -0.0000

Data Index: 1259794 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.6304. Min Act: -0.0000

Data Index: 1088269 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.6457. Min Act: -0.0000

Data Index: 397276 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.6124. Min Act: -0.0000

Data Index: 628706 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.6369. Min Act: -0.0000

Data Index: 369544 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.6303. Min Act: -0.0000

Data Index: 855870 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.6098. Min Act: -0.0000

Data Index: 729269 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.6096. Min Act: -0.0000

Data Index: 1220774 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.6027. Min Act: -0.0000

Data Index: 923489 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.5766. Min Act: -0.0000

Data Index: 875548 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.6013. Min Act: -0.0000

Data Index: 1237036 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.5567. Min Act: -0.0000

Data Index: 151735 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.5608. Min Act: -0.0000

Data Index: 1339862 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.5424. Min Act: -0.0000

Data Index: 976243 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.5485. Min Act: -0.0000

Data Index: 403816 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.5432. Min Act: -0.0000

Data Index: 234901 (C4 (Web Text))

Max Activating Token Index: 25