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

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

Neuron 3736 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.5688. Min Act: -0.0000

Data Index: 1003855 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4982. Min Act: -0.0000

Data Index: 1082830 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.5287. Min Act: -0.0000

Data Index: 427774 (C4 (Web Text))

Max Activating Token Index: 964

Text #3

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4901. Min Act: -0.0000

Data Index: 357799 (C4 (Web Text))

Max Activating Token Index: 638

Text #4

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.5433. Min Act: -0.0000

Data Index: 513651 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.5021. Min Act: -0.0000

Data Index: 703995 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.5311. Min Act: -0.0000

Data Index: 186091 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.5366. Min Act: -0.0000

Data Index: 901532 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.5078. Min Act: -0.0000

Data Index: 736045 (C4 (Web Text))

Max Activating Token Index: 494

Text #9

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4882. Min Act: -0.0000

Data Index: 686043 (C4 (Web Text))

Max Activating Token Index: 592

Text #10

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4673. Min Act: -0.0000

Data Index: 1063855 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.5042. Min Act: -0.0000

Data Index: 827290 (C4 (Web Text))

Max Activating Token Index: 624

Text #12

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4700. Min Act: -0.0000

Data Index: 810619 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4983. Min Act: -0.0000

Data Index: 179276 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4965. Min Act: -0.0000

Data Index: 256252 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4764. Min Act: -0.0000

Data Index: 1089416 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4508. Min Act: -0.0000

Data Index: 313430 (C4 (Web Text))

Max Activating Token Index: 257

Text #17

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4601. Min Act: -0.0000

Data Index: 1358417 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4617. Min Act: -0.0000

Data Index: 957642 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 0.5688. Min Range: -0.5688

Max Act: 0.4701. Min Act: -0.0000

Data Index: 1037056 (C4 (Web Text))

Max Activating Token Index: 332