Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1666 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2644. Min Act: -0.0001

Data Index: 648373 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2539. Min Act: -0.0001

Data Index: 1007474 (C4 (Web Text))

Max Activating Token Index: 278

Text #2

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2381. Min Act: -0.0000

Data Index: 331628 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2221. Min Act: -0.0000

Data Index: 652417 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2253. Min Act: -0.0000

Data Index: 461660 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2230. Min Act: -0.0000

Data Index: 1026698 (C4 (Web Text))

Max Activating Token Index: 521

Text #6

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2163. Min Act: -0.0001

Data Index: 970091 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2175. Min Act: -0.0001

Data Index: 89842 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2123. Min Act: -0.0001

Data Index: 246590 (C4 (Web Text))

Max Activating Token Index: 528

Text #9

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2057. Min Act: -0.0000

Data Index: 456921 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2121. Min Act: -0.0000

Data Index: 580495 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2090. Min Act: -0.0000

Data Index: 384417 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.1968. Min Act: -0.0001

Data Index: 1030978 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2186. Min Act: -0.0001

Data Index: 1221994 (C4 (Web Text))

Max Activating Token Index: 649

Text #14

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2143. Min Act: -0.0001

Data Index: 117047 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2118. Min Act: -0.0001

Data Index: 340117 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2010. Min Act: -0.0001

Data Index: 302717 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.1919. Min Act: -0.0001

Data Index: 904838 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2050. Min Act: -0.0001

Data Index: 663447 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2051. Min Act: -0.0001

Data Index: 279847 (C4 (Web Text))

Max Activating Token Index: 69