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

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

Neuron 3984 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: 0.3734. Min Range: -0.3734

Max Act: 0.3734. Min Act: -0.0001

Data Index: 1180552 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3641. Min Act: -0.0001

Data Index: 1310263 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3070. Min Act: -0.0001

Data Index: 998619 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3121. Min Act: -0.0001

Data Index: 928921 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.3035. Min Act: -0.0001

Data Index: 984908 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2991. Min Act: -0.0001

Data Index: 1324191 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2721. Min Act: -0.0001

Data Index: 1343238 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2869. Min Act: -0.0001

Data Index: 685736 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2638. Min Act: -0.0001

Data Index: 1154889 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2807. Min Act: -0.0002

Data Index: 140323 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2688. Min Act: -0.0001

Data Index: 586549 (C4 (Web Text))

Max Activating Token Index: 487

Text #11

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2791. Min Act: -0.0001

Data Index: 745730 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2751. Min Act: -0.0002

Data Index: 1015490 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2832. Min Act: -0.0001

Data Index: 168371 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2667. Min Act: -0.0001

Data Index: 1230912 (C4 (Web Text))

Max Activating Token Index: 604

Text #15

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2780. Min Act: -0.0001

Data Index: 389642 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2673. Min Act: -0.0001

Data Index: 1318914 (C4 (Web Text))

Max Activating Token Index: 861

Text #17

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2389. Min Act: -0.0001

Data Index: 792362 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2743. Min Act: -0.0001

Data Index: 637716 (C4 (Web Text))

Max Activating Token Index: 498

Text #19

Max Range: 0.3734. Min Range: -0.3734

Max Act: 0.2514. Min Act: -0.0001

Data Index: 720002 (C4 (Web Text))

Max Activating Token Index: 464