Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1978 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1144. Min Act: -0.0001

Data Index: 59641 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0892. Min Act: -0.0001

Data Index: 463739 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0825. Min Act: -0.0001

Data Index: 1278882 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0781. Min Act: -0.0001

Data Index: 518474 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0891. Min Act: -0.0001

Data Index: 549089 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0824. Min Act: -0.0001

Data Index: 465081 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0779. Min Act: -0.0001

Data Index: 26332 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0796. Min Act: -0.0001

Data Index: 1315233 (C4 (Web Text))

Max Activating Token Index: 785

Text #8

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0798. Min Act: -0.0001

Data Index: 448232 (C4 (Web Text))

Max Activating Token Index: 333

Text #9

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0756. Min Act: -0.0001

Data Index: 1307024 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0783. Min Act: -0.0001

Data Index: 406014 (C4 (Web Text))

Max Activating Token Index: 521

Text #11

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0781. Min Act: -0.0001

Data Index: 1130637 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0751. Min Act: -0.0001

Data Index: 423069 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0747. Min Act: -0.0001

Data Index: 725177 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0768. Min Act: -0.0001

Data Index: 314627 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0740. Min Act: -0.0001

Data Index: 1156628 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0792. Min Act: -0.0001

Data Index: 561275 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0761. Min Act: -0.0001

Data Index: 328263 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0774. Min Act: -0.0001

Data Index: 1277950 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0762. Min Act: -0.0001

Data Index: 1270890 (C4 (Web Text))

Max Activating Token Index: 496