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

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

Neuron 4985 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7881. Min Range: -4.7881

Max Act: 4.7881. Min Act: -0.0000

Data Index: 1344078 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 4.7881. Min Range: -4.7881

Max Act: 4.1159. Min Act: -0.0000

Data Index: 498246 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 4.7881. Min Range: -4.7881

Max Act: 4.0913. Min Act: -0.0000

Data Index: 280014 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 4.7881. Min Range: -4.7881

Max Act: 3.7839. Min Act: -0.0000

Data Index: 483865 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 4.7881. Min Range: -4.7881

Max Act: 3.4353. Min Act: -0.0000

Data Index: 692777 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 4.7881. Min Range: -4.7881

Max Act: 3.5693. Min Act: -0.0000

Data Index: 758340 (C4 (Web Text))

Max Activating Token Index: 877

Text #6

Max Range: 4.7881. Min Range: -4.7881

Max Act: 3.4088. Min Act: -0.0000

Data Index: 154702 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 4.7881. Min Range: -4.7881

Max Act: 3.3224. Min Act: -0.0000

Data Index: 1289149 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 4.7881. Min Range: -4.7881

Max Act: 3.1007. Min Act: -0.0000

Data Index: 578081 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 4.7881. Min Range: -4.7881

Max Act: 3.3024. Min Act: -0.0000

Data Index: 655778 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 4.7881. Min Range: -4.7881

Max Act: 3.1040. Min Act: -0.0000

Data Index: 1338850 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 4.7881. Min Range: -4.7881

Max Act: 2.7982. Min Act: -0.0000

Data Index: 1313652 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 4.7881. Min Range: -4.7881

Max Act: 3.3410. Min Act: -0.0000

Data Index: 47753 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 4.7881. Min Range: -4.7881

Max Act: 3.0665. Min Act: -0.0000

Data Index: 1337619 (C4 (Web Text))

Max Activating Token Index: 549

Text #14

Max Range: 4.7881. Min Range: -4.7881

Max Act: 3.1742. Min Act: -0.0000

Data Index: 641406 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 4.7881. Min Range: -4.7881

Max Act: 3.3814. Min Act: -0.0000

Data Index: 1015489 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 4.7881. Min Range: -4.7881

Max Act: 3.1143. Min Act: -0.0000

Data Index: 1211728 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 4.7881. Min Range: -4.7881

Max Act: 3.2691. Min Act: -0.0000

Data Index: 494770 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 4.7881. Min Range: -4.7881

Max Act: 3.0045. Min Act: -0.0000

Data Index: 165454 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 4.7881. Min Range: -4.7881

Max Act: 2.1518. Min Act: -0.0000

Data Index: 1323460 (C4 (Web Text))

Max Activating Token Index: 859