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

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

Neuron 5146 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.9185. Min Range: -7.9185

Max Act: 7.9044. Min Act: -0.0000

Data Index: 1006834 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 7.9185. Min Range: -7.9185

Max Act: 7.5849. Min Act: -0.0000

Data Index: 1341694 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 7.9185. Min Range: -7.9185

Max Act: 7.9185. Min Act: -0.0000

Data Index: 1207045 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 7.9185. Min Range: -7.9185

Max Act: 7.7202. Min Act: -0.0000

Data Index: 595774 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 7.9185. Min Range: -7.9185

Max Act: 7.6304. Min Act: -0.0000

Data Index: 166362 (C4 (Web Text))

Max Activating Token Index: 439

Text #5

Max Range: 7.9185. Min Range: -7.9185

Max Act: 7.3784. Min Act: -0.0000

Data Index: 1016397 (C4 (Web Text))

Max Activating Token Index: 294

Text #6

Max Range: 7.9185. Min Range: -7.9185

Max Act: 7.3474. Min Act: -0.0000

Data Index: 818246 (C4 (Web Text))

Max Activating Token Index: 604

Text #7

Max Range: 7.9185. Min Range: -7.9185

Max Act: 7.2430. Min Act: -0.0000

Data Index: 818006 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 7.9185. Min Range: -7.9185

Max Act: 7.4245. Min Act: -0.0000

Data Index: 1186690 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 7.9185. Min Range: -7.9185

Max Act: 7.5848. Min Act: -0.0000

Data Index: 990005 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 7.9185. Min Range: -7.9185

Max Act: 7.3924. Min Act: -0.0000

Data Index: 12535 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 7.9185. Min Range: -7.9185

Max Act: 7.2179. Min Act: -0.0000

Data Index: 1103383 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 7.9185. Min Range: -7.9185

Max Act: 7.1938. Min Act: -0.0000

Data Index: 376284 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 7.9185. Min Range: -7.9185

Max Act: 7.3754. Min Act: -0.0000

Data Index: 639882 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 7.9185. Min Range: -7.9185

Max Act: 7.2740. Min Act: -0.0000

Data Index: 853027 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 7.9185. Min Range: -7.9185

Max Act: 7.1069. Min Act: -0.0000

Data Index: 1000752 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 7.9185. Min Range: -7.9185

Max Act: 7.5574. Min Act: -0.0000

Data Index: 297507 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 7.9185. Min Range: -7.9185

Max Act: 7.2069. Min Act: -0.0000

Data Index: 698048 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 7.9185. Min Range: -7.9185

Max Act: 7.2166. Min Act: -0.0000

Data Index: 694708 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 7.9185. Min Range: -7.9185

Max Act: 6.9467. Min Act: -0.0000

Data Index: 257265 (C4 (Web Text))

Max Activating Token Index: 399