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

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

Neuron 2492 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4657. Min Range: -1.4657

Max Act: 1.4657. Min Act: -0.0001

Data Index: 545980 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 1.4657. Min Range: -1.4657

Max Act: 1.1533. Min Act: -0.0001

Data Index: 1330447 (C4 (Web Text))

Max Activating Token Index: 938

Text #2

Max Range: 1.4657. Min Range: -1.4657

Max Act: 1.2218. Min Act: -0.0001

Data Index: 48058 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 1.4657. Min Range: -1.4657

Max Act: 1.1817. Min Act: -0.0001

Data Index: 956200 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 1.4657. Min Range: -1.4657

Max Act: 1.1700. Min Act: -0.0001

Data Index: 878835 (C4 (Web Text))

Max Activating Token Index: 814

Text #5

Max Range: 1.4657. Min Range: -1.4657

Max Act: 1.0666. Min Act: -0.0000

Data Index: 968853 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 1.4657. Min Range: -1.4657

Max Act: 1.2231. Min Act: -0.0001

Data Index: 309501 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 1.4657. Min Range: -1.4657

Max Act: 1.1977. Min Act: -0.0001

Data Index: 352876 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 1.4657. Min Range: -1.4657

Max Act: 1.2219. Min Act: -0.0001

Data Index: 1005797 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 1.4657. Min Range: -1.4657

Max Act: 1.2013. Min Act: -0.0001

Data Index: 371708 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 1.4657. Min Range: -1.4657

Max Act: 1.2008. Min Act: -0.0001

Data Index: 817223 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 1.4657. Min Range: -1.4657

Max Act: 1.1187. Min Act: -0.0000

Data Index: 1358258 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 1.4657. Min Range: -1.4657

Max Act: 1.1108. Min Act: -0.0001

Data Index: 896162 (C4 (Web Text))

Max Activating Token Index: 612

Text #13

Max Range: 1.4657. Min Range: -1.4657

Max Act: 1.0711. Min Act: -0.0001

Data Index: 264269 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 1.4657. Min Range: -1.4657

Max Act: 1.0372. Min Act: -0.0001

Data Index: 952244 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 1.4657. Min Range: -1.4657

Max Act: 1.0226. Min Act: -0.0000

Data Index: 658040 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 1.4657. Min Range: -1.4657

Max Act: 1.0668. Min Act: -0.0001

Data Index: 812150 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 1.4657. Min Range: -1.4657

Max Act: 0.9667. Min Act: -0.0001

Data Index: 786923 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 1.4657. Min Range: -1.4657

Max Act: 0.8793. Min Act: -0.0001

Data Index: 1321345 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 1.4657. Min Range: -1.4657

Max Act: 0.9434. Min Act: -0.0001

Data Index: 740147 (C4 (Web Text))

Max Activating Token Index: 801