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

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

Neuron 4106 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2788. Min Range: -0.2788

Max Act: 0.2788. Min Act: -0.0002

Data Index: 1168265 (C4 (Web Text))

Max Activating Token Index: 398

Text #1

Max Range: 0.2788. Min Range: -0.2788

Max Act: 0.2487. Min Act: -0.0002

Data Index: 953673 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 0.2788. Min Range: -0.2788

Max Act: 0.2456. Min Act: -0.0002

Data Index: 72247 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 0.2788. Min Range: -0.2788

Max Act: 0.2413. Min Act: -0.0002

Data Index: 611407 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 0.2788. Min Range: -0.2788

Max Act: 0.1986. Min Act: -0.0002

Data Index: 534565 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 0.2788. Min Range: -0.2788

Max Act: 0.2424. Min Act: -0.0002

Data Index: 58966 (C4 (Web Text))

Max Activating Token Index: 100

Text #6

Max Range: 0.2788. Min Range: -0.2788

Max Act: 0.2180. Min Act: -0.0002

Data Index: 1340058 (C4 (Web Text))

Max Activating Token Index: 513

Text #7

Max Range: 0.2788. Min Range: -0.2788

Max Act: 0.2272. Min Act: -0.0002

Data Index: 685634 (C4 (Web Text))

Max Activating Token Index: 772

Text #8

Max Range: 0.2788. Min Range: -0.2788

Max Act: 0.1990. Min Act: -0.0002

Data Index: 734839 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 0.2788. Min Range: -0.2788

Max Act: 0.1897. Min Act: -0.0002

Data Index: 1266972 (C4 (Web Text))

Max Activating Token Index: 812

Text #10

Max Range: 0.2788. Min Range: -0.2788

Max Act: 0.2087. Min Act: -0.0002

Data Index: 1306284 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 0.2788. Min Range: -0.2788

Max Act: 0.2102. Min Act: -0.0002

Data Index: 17469 (C4 (Web Text))

Max Activating Token Index: 519

Text #12

Max Range: 0.2788. Min Range: -0.2788

Max Act: 0.2029. Min Act: -0.0002

Data Index: 4731 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 0.2788. Min Range: -0.2788

Max Act: 0.2007. Min Act: -0.0002

Data Index: 342132 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 0.2788. Min Range: -0.2788

Max Act: 0.1789. Min Act: -0.0002

Data Index: 1278753 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 0.2788. Min Range: -0.2788

Max Act: 0.1864. Min Act: -0.0002

Data Index: 901440 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 0.2788. Min Range: -0.2788

Max Act: 0.1863. Min Act: -0.0002

Data Index: 940650 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 0.2788. Min Range: -0.2788

Max Act: 0.2050. Min Act: -0.0002

Data Index: 1188894 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 0.2788. Min Range: -0.2788

Max Act: 0.2222. Min Act: -0.0002

Data Index: 82994 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 0.2788. Min Range: -0.2788

Max Act: 0.1798. Min Act: -0.0002

Data Index: 852128 (C4 (Web Text))

Max Activating Token Index: 162