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

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

Neuron 5109 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: 0.8410. Min Range: -0.8410

Max Act: 0.8410. Min Act: -0.0002

Data Index: 1057580 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.7804. Min Act: -0.0002

Data Index: 760277 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.6658. Min Act: -0.0002

Data Index: 1233002 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.7322. Min Act: -0.0002

Data Index: 679871 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.6824. Min Act: -0.0002

Data Index: 991095 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.6773. Min Act: -0.0002

Data Index: 189957 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.6601. Min Act: -0.0002

Data Index: 107129 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.6525. Min Act: -0.0002

Data Index: 643976 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.6352. Min Act: -0.0002

Data Index: 541827 (C4 (Web Text))

Max Activating Token Index: 709

Text #9

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.6301. Min Act: -0.0002

Data Index: 808466 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.6623. Min Act: -0.0002

Data Index: 1276017 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.5990. Min Act: -0.0002

Data Index: 842627 (C4 (Web Text))

Max Activating Token Index: 215

Text #12

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.6367. Min Act: -0.0002

Data Index: 647930 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.5939. Min Act: -0.0002

Data Index: 166460 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.6115. Min Act: -0.0002

Data Index: 17565 (C4 (Web Text))

Max Activating Token Index: 99

Text #15

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.6306. Min Act: -0.0002

Data Index: 1114256 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.6024. Min Act: -0.0002

Data Index: 943265 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.6197. Min Act: -0.0002

Data Index: 397399 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.5995. Min Act: -0.0002

Data Index: 95358 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 0.8410. Min Range: -0.8410

Max Act: 0.6015. Min Act: -0.0002

Data Index: 692480 (C4 (Web Text))

Max Activating Token Index: 327