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

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

Neuron 5587 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.5785. Min Act: -0.0000

Data Index: 338903 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.5554. Min Act: -0.0000

Data Index: 1289971 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.5253. Min Act: -0.0000

Data Index: 914208 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.4710. Min Act: -0.0000

Data Index: 218378 (C4 (Web Text))

Max Activating Token Index: 311

Text #4

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.4618. Min Act: -0.0000

Data Index: 706400 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.4443. Min Act: -0.0000

Data Index: 842903 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.4164. Min Act: -0.0000

Data Index: 962099 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.4136. Min Act: -0.0000

Data Index: 725238 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.3811. Min Act: -0.0000

Data Index: 765926 (C4 (Web Text))

Max Activating Token Index: 350

Text #9

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.4065. Min Act: -0.0000

Data Index: 1037892 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.4345. Min Act: -0.0000

Data Index: 905078 (C4 (Web Text))

Max Activating Token Index: 644

Text #11

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.4203. Min Act: -0.0000

Data Index: 1201834 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.4086. Min Act: -0.0000

Data Index: 1172838 (C4 (Web Text))

Max Activating Token Index: 450

Text #13

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.3616. Min Act: -0.0000

Data Index: 1228602 (C4 (Web Text))

Max Activating Token Index: 468

Text #14

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.3519. Min Act: -0.0000

Data Index: 751044 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.4068. Min Act: -0.0000

Data Index: 256176 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.3937. Min Act: -0.0000

Data Index: 373869 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.4027. Min Act: -0.0000

Data Index: 549459 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.4294. Min Act: -0.0000

Data Index: 252119 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.3702. Min Act: -0.0000

Data Index: 148848 (C4 (Web Text))

Max Activating Token Index: 919