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

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

Neuron 550 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1213. Min Act: -0.0001

Data Index: 773139 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1105. Min Act: -0.0001

Data Index: 878183 (C4 (Web Text))

Max Activating Token Index: 904

Text #2

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0978. Min Act: -0.0001

Data Index: 1369434 (Python Code)

Max Activating Token Index: 678

Text #3

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1012. Min Act: -0.0001

Data Index: 1534072 (Python Code)

Max Activating Token Index: 101

Text #4

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1012. Min Act: -0.0001

Data Index: 1056014 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0772. Min Act: -0.0001

Data Index: 676601 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0885. Min Act: -0.0001

Data Index: 649567 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0887. Min Act: -0.0001

Data Index: 1413480 (Python Code)

Max Activating Token Index: 376

Text #8

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0800. Min Act: -0.0001

Data Index: 893036 (C4 (Web Text))

Max Activating Token Index: 754

Text #9

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0820. Min Act: -0.0001

Data Index: 1454404 (Python Code)

Max Activating Token Index: 777

Text #10

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0751. Min Act: -0.0001

Data Index: 297408 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0859. Min Act: -0.0001

Data Index: 550312 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0793. Min Act: -0.0001

Data Index: 1387758 (Python Code)

Max Activating Token Index: 314

Text #13

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0825. Min Act: -0.0001

Data Index: 1518510 (Python Code)

Max Activating Token Index: 970

Text #14

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0824. Min Act: -0.0001

Data Index: 1439309 (Python Code)

Max Activating Token Index: 642

Text #15

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0808. Min Act: -0.0001

Data Index: 1142587 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0774. Min Act: -0.0001

Data Index: 1619316 (Python Code)

Max Activating Token Index: 789

Text #17

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0812. Min Act: -0.0001

Data Index: 1517353 (Python Code)

Max Activating Token Index: 572

Text #18

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0777. Min Act: -0.0001

Data Index: 364788 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0833. Min Act: -0.0001

Data Index: 1405300 (Python Code)

Max Activating Token Index: 296