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

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

Neuron 486 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.6814. Min Act: -0.0000

Data Index: 999974 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.6355. Min Act: -0.0000

Data Index: 1220820 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.6146. Min Act: -0.0000

Data Index: 1090073 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5914. Min Act: -0.0000

Data Index: 345225 (C4 (Web Text))

Max Activating Token Index: 750

Text #4

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.6064. Min Act: -0.0000

Data Index: 480206 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5689. Min Act: -0.0000

Data Index: 1315236 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5502. Min Act: 0.0000

Data Index: 1244138 (C4 (Web Text))

Max Activating Token Index: 780

Text #7

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5501. Min Act: -0.0000

Data Index: 486369 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5479. Min Act: -0.0000

Data Index: 385700 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5616. Min Act: 0.0000

Data Index: 225844 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5542. Min Act: 0.0000

Data Index: 117822 (C4 (Web Text))

Max Activating Token Index: 661

Text #11

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5347. Min Act: -0.0000

Data Index: 138366 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5068. Min Act: -0.0000

Data Index: 390501 (C4 (Web Text))

Max Activating Token Index: 405

Text #13

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.4885. Min Act: -0.0000

Data Index: 920314 (C4 (Web Text))

Max Activating Token Index: 798

Text #14

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5163. Min Act: -0.0000

Data Index: 688873 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.4986. Min Act: -0.0000

Data Index: 257350 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5292. Min Act: -0.0000

Data Index: 1098074 (C4 (Web Text))

Max Activating Token Index: 861

Text #17

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5151. Min Act: -0.0000

Data Index: 478132 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5133. Min Act: -0.0000

Data Index: 307223 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 0.6814. Min Range: -0.6814

Max Act: 0.5178. Min Act: -0.0000

Data Index: 119075 (C4 (Web Text))

Max Activating Token Index: 815