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

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

Neuron 4992 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.5059. Min Act: -0.0000

Data Index: 657387 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.4044. Min Act: -0.0000

Data Index: 816877 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.2206. Min Act: -0.0000

Data Index: 1261050 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.1646. Min Act: -0.0000

Data Index: 1111178 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.1927. Min Act: -0.0000

Data Index: 154437 (C4 (Web Text))

Max Activating Token Index: 871

Text #5

Max Range: 1.5059. Min Range: -1.5059

Max Act: 0.9872. Min Act: -0.0000

Data Index: 433498 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.1519. Min Act: -0.0000

Data Index: 885802 (C4 (Web Text))

Max Activating Token Index: 954

Text #7

Max Range: 1.5059. Min Range: -1.5059

Max Act: 0.9677. Min Act: -0.0000

Data Index: 621298 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.1199. Min Act: -0.0000

Data Index: 1341014 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 1.5059. Min Range: -1.5059

Max Act: 0.9563. Min Act: -0.0000

Data Index: 314109 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 1.5059. Min Range: -1.5059

Max Act: 0.9217. Min Act: -0.0000

Data Index: 782060 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 1.5059. Min Range: -1.5059

Max Act: 0.9626. Min Act: -0.0000

Data Index: 1617859 (Python Code)

Max Activating Token Index: 681

Text #12

Max Range: 1.5059. Min Range: -1.5059

Max Act: 0.9857. Min Act: -0.0000

Data Index: 1606769 (Python Code)

Max Activating Token Index: 679

Text #13

Max Range: 1.5059. Min Range: -1.5059

Max Act: 0.8801. Min Act: -0.0000

Data Index: 554248 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 1.5059. Min Range: -1.5059

Max Act: 0.8861. Min Act: -0.0000

Data Index: 1392841 (Python Code)

Max Activating Token Index: 249

Text #15

Max Range: 1.5059. Min Range: -1.5059

Max Act: 0.9556. Min Act: -0.0000

Data Index: 1632214 (Python Code)

Max Activating Token Index: 769

Text #16

Max Range: 1.5059. Min Range: -1.5059

Max Act: 0.9610. Min Act: -0.0000

Data Index: 1631616 (Python Code)

Max Activating Token Index: 296

Text #17

Max Range: 1.5059. Min Range: -1.5059

Max Act: 0.9001. Min Act: -0.0000

Data Index: 1507792 (Python Code)

Max Activating Token Index: 524

Text #18

Max Range: 1.5059. Min Range: -1.5059

Max Act: 0.9182. Min Act: -0.0000

Data Index: 1385710 (Python Code)

Max Activating Token Index: 718

Text #19

Max Range: 1.5059. Min Range: -1.5059

Max Act: 0.9586. Min Act: -0.0000

Data Index: 385840 (C4 (Web Text))

Max Activating Token Index: 963