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

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

Neuron 1554 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.5864. Min Act: -0.0000

Data Index: 1032363 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.5643. Min Act: -0.0000

Data Index: 1308863 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.5662. Min Act: -0.0000

Data Index: 372324 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.5266. Min Act: -0.0000

Data Index: 1234992 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.5319. Min Act: -0.0000

Data Index: 566740 (C4 (Web Text))

Max Activating Token Index: 565

Text #5

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.5151. Min Act: -0.0000

Data Index: 71509 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.5245. Min Act: -0.0000

Data Index: 888456 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.5180. Min Act: -0.0000

Data Index: 1357596 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.4995. Min Act: -0.0000

Data Index: 1320618 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.5132. Min Act: -0.0000

Data Index: 737548 (C4 (Web Text))

Max Activating Token Index: 872

Text #10

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.5276. Min Act: -0.0000

Data Index: 759614 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.4932. Min Act: -0.0000

Data Index: 69804 (C4 (Web Text))

Max Activating Token Index: 455

Text #12

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.4846. Min Act: -0.0000

Data Index: 495781 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.4915. Min Act: -0.0000

Data Index: 801663 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.4684. Min Act: -0.0000

Data Index: 459235 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.4998. Min Act: -0.0000

Data Index: 226808 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.4890. Min Act: -0.0000

Data Index: 970299 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.4910. Min Act: -0.0000

Data Index: 1240975 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.5040. Min Act: -0.0000

Data Index: 987798 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.4884. Min Act: -0.0000

Data Index: 239291 (C4 (Web Text))

Max Activating Token Index: 479