Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1079 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3721. Min Act: -0.0002

Data Index: 741239 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2917. Min Act: -0.0002

Data Index: 334779 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3098. Min Act: -0.0002

Data Index: 1352893 (C4 (Web Text))

Max Activating Token Index: 540

Text #3

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3204. Min Act: -0.0002

Data Index: 646609 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2971. Min Act: -0.0002

Data Index: 290601 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.3178. Min Act: -0.0002

Data Index: 519323 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2900. Min Act: -0.0002

Data Index: 1236087 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2692. Min Act: -0.0002

Data Index: 1250803 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2905. Min Act: -0.0002

Data Index: 798732 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2676. Min Act: -0.0002

Data Index: 5947 (C4 (Web Text))

Max Activating Token Index: 1007

Text #10

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2682. Min Act: -0.0002

Data Index: 112185 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2660. Min Act: -0.0002

Data Index: 1326647 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2503. Min Act: -0.0002

Data Index: 814570 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2486. Min Act: -0.0002

Data Index: 655370 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2552. Min Act: -0.0002

Data Index: 1239086 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2532. Min Act: -0.0002

Data Index: 25060 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2715. Min Act: -0.0002

Data Index: 176520 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2681. Min Act: -0.0002

Data Index: 1338955 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2651. Min Act: -0.0002

Data Index: 1101401 (C4 (Web Text))

Max Activating Token Index: 804

Text #19

Max Range: 0.3721. Min Range: -0.3721

Max Act: 0.2508. Min Act: -0.0002

Data Index: 310099 (C4 (Web Text))

Max Activating Token Index: 236