Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 857 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.0989. Min Range: -3.0989

Max Act: 2.9532. Min Act: -0.0000

Data Index: 579833 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 3.0989. Min Range: -3.0989

Max Act: 3.0989. Min Act: -0.0000

Data Index: 1180506 (C4 (Web Text))

Max Activating Token Index: 531

Text #2

Max Range: 3.0989. Min Range: -3.0989

Max Act: 2.8944. Min Act: -0.0000

Data Index: 1342594 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 3.0989. Min Range: -3.0989

Max Act: 2.6387. Min Act: -0.0000

Data Index: 715889 (C4 (Web Text))

Max Activating Token Index: 822

Text #4

Max Range: 3.0989. Min Range: -3.0989

Max Act: 2.6267. Min Act: -0.0000

Data Index: 785607 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 3.0989. Min Range: -3.0989

Max Act: 2.3524. Min Act: -0.0000

Data Index: 1324136 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 3.0989. Min Range: -3.0989

Max Act: 2.3267. Min Act: -0.0000

Data Index: 1206925 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 3.0989. Min Range: -3.0989

Max Act: 2.2839. Min Act: -0.0000

Data Index: 1195601 (C4 (Web Text))

Max Activating Token Index: 958

Text #8

Max Range: 3.0989. Min Range: -3.0989

Max Act: 2.2503. Min Act: -0.0000

Data Index: 693494 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 3.0989. Min Range: -3.0989

Max Act: 2.2022. Min Act: -0.0000

Data Index: 1063763 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 3.0989. Min Range: -3.0989

Max Act: 1.9234. Min Act: -0.0000

Data Index: 602491 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 3.0989. Min Range: -3.0989

Max Act: 2.1277. Min Act: -0.0000

Data Index: 421106 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 3.0989. Min Range: -3.0989

Max Act: 2.0539. Min Act: -0.0000

Data Index: 325913 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 3.0989. Min Range: -3.0989

Max Act: 2.0284. Min Act: -0.0000

Data Index: 1274866 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 3.0989. Min Range: -3.0989

Max Act: 1.8918. Min Act: -0.0000

Data Index: 634740 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 3.0989. Min Range: -3.0989

Max Act: 1.8524. Min Act: -0.0000

Data Index: 1001620 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 3.0989. Min Range: -3.0989

Max Act: 1.7169. Min Act: -0.0000

Data Index: 1304764 (C4 (Web Text))

Max Activating Token Index: 637

Text #17

Max Range: 3.0989. Min Range: -3.0989

Max Act: 1.7959. Min Act: -0.0000

Data Index: 1055596 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 3.0989. Min Range: -3.0989

Max Act: 1.9773. Min Act: -0.0000

Data Index: 898984 (C4 (Web Text))

Max Activating Token Index: 265

Text #19

Max Range: 3.0989. Min Range: -3.0989

Max Act: 1.6707. Min Act: -0.0000

Data Index: 161152 (C4 (Web Text))

Max Activating Token Index: 192