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

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

Neuron 1725 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3899. Min Range: -0.3899

Max Act: 0.3899. Min Act: -0.0000

Data Index: 600249 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 0.3899. Min Range: -0.3899

Max Act: 0.3716. Min Act: -0.0000

Data Index: 1159703 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 0.3899. Min Range: -0.3899

Max Act: 0.3282. Min Act: -0.0000

Data Index: 855201 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 0.3899. Min Range: -0.3899

Max Act: 0.3299. Min Act: -0.0000

Data Index: 847572 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 0.3899. Min Range: -0.3899

Max Act: 0.3196. Min Act: -0.0000

Data Index: 386382 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 0.3899. Min Range: -0.3899

Max Act: 0.3189. Min Act: -0.0000

Data Index: 304891 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 0.3899. Min Range: -0.3899

Max Act: 0.3106. Min Act: -0.0000

Data Index: 1298787 (C4 (Web Text))

Max Activating Token Index: 67

Text #7

Max Range: 0.3899. Min Range: -0.3899

Max Act: 0.3156. Min Act: -0.0000

Data Index: 716783 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 0.3899. Min Range: -0.3899

Max Act: 0.2951. Min Act: -0.0000

Data Index: 295948 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 0.3899. Min Range: -0.3899

Max Act: 0.2768. Min Act: -0.0000

Data Index: 119978 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 0.3899. Min Range: -0.3899

Max Act: 0.2949. Min Act: -0.0000

Data Index: 802656 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 0.3899. Min Range: -0.3899

Max Act: 0.2839. Min Act: -0.0000

Data Index: 218582 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 0.3899. Min Range: -0.3899

Max Act: 0.2725. Min Act: -0.0000

Data Index: 933575 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 0.3899. Min Range: -0.3899

Max Act: 0.2726. Min Act: -0.0000

Data Index: 684140 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 0.3899. Min Range: -0.3899

Max Act: 0.2895. Min Act: -0.0000

Data Index: 954862 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 0.3899. Min Range: -0.3899

Max Act: 0.2685. Min Act: -0.0000

Data Index: 1174448 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 0.3899. Min Range: -0.3899

Max Act: 0.2886. Min Act: -0.0000

Data Index: 646034 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 0.3899. Min Range: -0.3899

Max Act: 0.2709. Min Act: -0.0000

Data Index: 461129 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 0.3899. Min Range: -0.3899

Max Act: 0.2792. Min Act: -0.0000

Data Index: 40738 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 0.3899. Min Range: -0.3899

Max Act: 0.2753. Min Act: -0.0000

Data Index: 38184 (C4 (Web Text))

Max Activating Token Index: 768