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

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

Neuron 3914 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.5475. Min Act: -0.0002

Data Index: 667787 (C4 (Web Text))

Max Activating Token Index: 388

Text #1

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.4634. Min Act: -0.0002

Data Index: 856853 (C4 (Web Text))

Max Activating Token Index: 871

Text #2

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.4530. Min Act: -0.0002

Data Index: 542187 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.4414. Min Act: -0.0002

Data Index: 1333368 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.4406. Min Act: -0.0002

Data Index: 493776 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.3604. Min Act: -0.0002

Data Index: 860453 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.4253. Min Act: -0.0002

Data Index: 483890 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.4063. Min Act: -0.0002

Data Index: 753962 (C4 (Web Text))

Max Activating Token Index: 508

Text #8

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.3781. Min Act: -0.0002

Data Index: 895754 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.3464. Min Act: -0.0002

Data Index: 1186191 (C4 (Web Text))

Max Activating Token Index: 980

Text #10

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.4555. Min Act: -0.0002

Data Index: 679993 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.3988. Min Act: -0.0002

Data Index: 1251273 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.4158. Min Act: -0.0002

Data Index: 1229793 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.4119. Min Act: -0.0002

Data Index: 1178854 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.4324. Min Act: -0.0002

Data Index: 1183270 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.3802. Min Act: -0.0002

Data Index: 616941 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.3865. Min Act: -0.0002

Data Index: 588889 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.4225. Min Act: -0.0002

Data Index: 638231 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.3736. Min Act: -0.0002

Data Index: 716099 (C4 (Web Text))

Max Activating Token Index: 543

Text #19

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.3500. Min Act: -0.0002

Data Index: 162353 (C4 (Web Text))

Max Activating Token Index: 624