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

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

Neuron 4845 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2663. Min Range: -3.2663

Max Act: 3.2663. Min Act: -0.0000

Data Index: 814664 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 3.2663. Min Range: -3.2663

Max Act: 2.9273. Min Act: -0.0000

Data Index: 265603 (C4 (Web Text))

Max Activating Token Index: 440

Text #2

Max Range: 3.2663. Min Range: -3.2663

Max Act: 2.8255. Min Act: -0.0000

Data Index: 2891 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 3.2663. Min Range: -3.2663

Max Act: 2.8036. Min Act: -0.0000

Data Index: 448881 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 3.2663. Min Range: -3.2663

Max Act: 2.5904. Min Act: -0.0000

Data Index: 986609 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 3.2663. Min Range: -3.2663

Max Act: 2.5457. Min Act: -0.0000

Data Index: 321335 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 3.2663. Min Range: -3.2663

Max Act: 2.4401. Min Act: -0.0000

Data Index: 629817 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 3.2663. Min Range: -3.2663

Max Act: 2.4161. Min Act: -0.0000

Data Index: 607834 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 3.2663. Min Range: -3.2663

Max Act: 2.2758. Min Act: -0.0000

Data Index: 373775 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 3.2663. Min Range: -3.2663

Max Act: 2.1243. Min Act: -0.0000

Data Index: 1057645 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 3.2663. Min Range: -3.2663

Max Act: 2.3562. Min Act: -0.0000

Data Index: 416700 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 3.2663. Min Range: -3.2663

Max Act: 2.3225. Min Act: -0.0000

Data Index: 587866 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 3.2663. Min Range: -3.2663

Max Act: 2.1789. Min Act: -0.0000

Data Index: 1030437 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 3.2663. Min Range: -3.2663

Max Act: 2.1496. Min Act: -0.0000

Data Index: 1202759 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 3.2663. Min Range: -3.2663

Max Act: 2.0082. Min Act: -0.0001

Data Index: 426902 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 3.2663. Min Range: -3.2663

Max Act: 2.2262. Min Act: -0.0000

Data Index: 1248904 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 3.2663. Min Range: -3.2663

Max Act: 1.8837. Min Act: -0.0000

Data Index: 232266 (C4 (Web Text))

Max Activating Token Index: 308

Text #17

Max Range: 3.2663. Min Range: -3.2663

Max Act: 2.0882. Min Act: -0.0000

Data Index: 145214 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 3.2663. Min Range: -3.2663

Max Act: 2.2013. Min Act: -0.0000

Data Index: 845159 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 3.2663. Min Range: -3.2663

Max Act: 1.9679. Min Act: -0.0000

Data Index: 321482 (C4 (Web Text))

Max Activating Token Index: 406