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

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

Neuron 580 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1337. Min Act: -0.0001

Data Index: 1244536 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1261. Min Act: -0.0001

Data Index: 113829 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1279. Min Act: -0.0001

Data Index: 565914 (C4 (Web Text))

Max Activating Token Index: 315

Text #3

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0952. Min Act: -0.0002

Data Index: 551254 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0925. Min Act: -0.0002

Data Index: 238290 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0926. Min Act: -0.0002

Data Index: 517540 (C4 (Web Text))

Max Activating Token Index: 586

Text #6

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0860. Min Act: -0.0002

Data Index: 912629 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0919. Min Act: -0.0002

Data Index: 181090 (C4 (Web Text))

Max Activating Token Index: 882

Text #8

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0884. Min Act: -0.0002

Data Index: 161381 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0837. Min Act: -0.0002

Data Index: 1071273 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0878. Min Act: -0.0002

Data Index: 890030 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0818. Min Act: -0.0002

Data Index: 147079 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0820. Min Act: -0.0001

Data Index: 221926 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0885. Min Act: -0.0001

Data Index: 1113865 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0791. Min Act: -0.0002

Data Index: 127852 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0876. Min Act: -0.0002

Data Index: 1093891 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0819. Min Act: -0.0002

Data Index: 94436 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0815. Min Act: -0.0002

Data Index: 313244 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0786. Min Act: -0.0001

Data Index: 487145 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0828. Min Act: -0.0002

Data Index: 1350010 (C4 (Web Text))

Max Activating Token Index: 947