Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2829 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.2799. Min Range: -5.2799

Max Act: 5.2799. Min Act: -0.0001

Data Index: 1222501 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 5.2799. Min Range: -5.2799

Max Act: 4.7533. Min Act: -0.0001

Data Index: 1024609 (C4 (Web Text))

Max Activating Token Index: 238

Text #2

Max Range: 5.2799. Min Range: -5.2799

Max Act: 4.1627. Min Act: -0.0001

Data Index: 374992 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 5.2799. Min Range: -5.2799

Max Act: 4.1746. Min Act: -0.0001

Data Index: 840207 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 5.2799. Min Range: -5.2799

Max Act: 4.2903. Min Act: -0.0001

Data Index: 813096 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 5.2799. Min Range: -5.2799

Max Act: 3.2929. Min Act: -0.0001

Data Index: 436124 (C4 (Web Text))

Max Activating Token Index: 904

Text #6

Max Range: 5.2799. Min Range: -5.2799

Max Act: 3.5537. Min Act: -0.0001

Data Index: 783878 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 5.2799. Min Range: -5.2799

Max Act: 3.5285. Min Act: -0.0001

Data Index: 960105 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 5.2799. Min Range: -5.2799

Max Act: 3.8123. Min Act: -0.0001

Data Index: 1279828 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 5.2799. Min Range: -5.2799

Max Act: 3.6632. Min Act: -0.0001

Data Index: 1066595 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 5.2799. Min Range: -5.2799

Max Act: 3.6255. Min Act: -0.0001

Data Index: 960010 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 5.2799. Min Range: -5.2799

Max Act: 3.4653. Min Act: -0.0001

Data Index: 519587 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 5.2799. Min Range: -5.2799

Max Act: 3.6045. Min Act: -0.0001

Data Index: 454467 (C4 (Web Text))

Max Activating Token Index: 834

Text #13

Max Range: 5.2799. Min Range: -5.2799

Max Act: 3.5797. Min Act: -0.0001

Data Index: 890025 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 5.2799. Min Range: -5.2799

Max Act: 3.6639. Min Act: -0.0001

Data Index: 1196857 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 5.2799. Min Range: -5.2799

Max Act: 3.2371. Min Act: -0.0001

Data Index: 225567 (C4 (Web Text))

Max Activating Token Index: 258

Text #16

Max Range: 5.2799. Min Range: -5.2799

Max Act: 3.6694. Min Act: -0.0001

Data Index: 153333 (C4 (Web Text))

Max Activating Token Index: 716

Text #17

Max Range: 5.2799. Min Range: -5.2799

Max Act: 3.1900. Min Act: -0.0001

Data Index: 972934 (C4 (Web Text))

Max Activating Token Index: 777

Text #18

Max Range: 5.2799. Min Range: -5.2799

Max Act: 3.3631. Min Act: -0.0001

Data Index: 56083 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 5.2799. Min Range: -5.2799

Max Act: 3.6507. Min Act: -0.0001

Data Index: 1014777 (C4 (Web Text))

Max Activating Token Index: 298