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

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

Neuron 526 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5354. Min Range: -1.5354

Max Act: 1.5354. Min Act: -0.0000

Data Index: 1342457 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 1.5354. Min Range: -1.5354

Max Act: 1.4122. Min Act: -0.0000

Data Index: 833941 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 1.5354. Min Range: -1.5354

Max Act: 1.2885. Min Act: -0.0000

Data Index: 916926 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 1.5354. Min Range: -1.5354

Max Act: 1.1140. Min Act: -0.0000

Data Index: 791723 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 1.5354. Min Range: -1.5354

Max Act: 1.0905. Min Act: -0.0000

Data Index: 819163 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 1.5354. Min Range: -1.5354

Max Act: 0.9911. Min Act: -0.0000

Data Index: 397846 (C4 (Web Text))

Max Activating Token Index: 504

Text #6

Max Range: 1.5354. Min Range: -1.5354

Max Act: 1.0151. Min Act: -0.0000

Data Index: 197585 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 1.5354. Min Range: -1.5354

Max Act: 1.0366. Min Act: -0.0000

Data Index: 1186995 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 1.5354. Min Range: -1.5354

Max Act: 0.9453. Min Act: -0.0000

Data Index: 800717 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 1.5354. Min Range: -1.5354

Max Act: 0.9724. Min Act: -0.0000

Data Index: 301051 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 1.5354. Min Range: -1.5354

Max Act: 0.9290. Min Act: -0.0000

Data Index: 760699 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 1.5354. Min Range: -1.5354

Max Act: 0.8618. Min Act: -0.0000

Data Index: 23311 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 1.5354. Min Range: -1.5354

Max Act: 0.9079. Min Act: -0.0000

Data Index: 128903 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 1.5354. Min Range: -1.5354

Max Act: 0.8746. Min Act: -0.0000

Data Index: 618627 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 1.5354. Min Range: -1.5354

Max Act: 0.8167. Min Act: -0.0000

Data Index: 547310 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 1.5354. Min Range: -1.5354

Max Act: 0.9249. Min Act: -0.0000

Data Index: 521235 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 1.5354. Min Range: -1.5354

Max Act: 0.8987. Min Act: -0.0000

Data Index: 1084426 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 1.5354. Min Range: -1.5354

Max Act: 0.9164. Min Act: -0.0000

Data Index: 933943 (C4 (Web Text))

Max Activating Token Index: 274

Text #18

Max Range: 1.5354. Min Range: -1.5354

Max Act: 0.8828. Min Act: -0.0000

Data Index: 995044 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 1.5354. Min Range: -1.5354

Max Act: 0.8800. Min Act: -0.0000

Data Index: 299499 (C4 (Web Text))

Max Activating Token Index: 105