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

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

Neuron 1532 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.7687. Min Range: -6.7687

Max Act: 6.7687. Min Act: -0.0000

Data Index: 389658 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 6.7687. Min Range: -6.7687

Max Act: 6.3231. Min Act: -0.0000

Data Index: 289794 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 6.7687. Min Range: -6.7687

Max Act: 5.9734. Min Act: -0.0000

Data Index: 727969 (C4 (Web Text))

Max Activating Token Index: 482

Text #3

Max Range: 6.7687. Min Range: -6.7687

Max Act: 5.4030. Min Act: -0.0000

Data Index: 1322226 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 6.7687. Min Range: -6.7687

Max Act: 5.0403. Min Act: -0.0000

Data Index: 1311193 (C4 (Web Text))

Max Activating Token Index: 397

Text #5

Max Range: 6.7687. Min Range: -6.7687

Max Act: 5.0143. Min Act: -0.0000

Data Index: 260923 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 6.7687. Min Range: -6.7687

Max Act: 4.8380. Min Act: -0.0000

Data Index: 180563 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 6.7687. Min Range: -6.7687

Max Act: 4.5485. Min Act: -0.0000

Data Index: 12854 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 6.7687. Min Range: -6.7687

Max Act: 4.5886. Min Act: -0.0000

Data Index: 1088761 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 6.7687. Min Range: -6.7687

Max Act: 4.9530. Min Act: -0.0000

Data Index: 578108 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 6.7687. Min Range: -6.7687

Max Act: 4.4876. Min Act: -0.0000

Data Index: 1197014 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 6.7687. Min Range: -6.7687

Max Act: 4.6251. Min Act: -0.0000

Data Index: 884200 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 6.7687. Min Range: -6.7687

Max Act: 4.2754. Min Act: -0.0000

Data Index: 582268 (C4 (Web Text))

Max Activating Token Index: 402

Text #13

Max Range: 6.7687. Min Range: -6.7687

Max Act: 4.2155. Min Act: -0.0000

Data Index: 7467 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 6.7687. Min Range: -6.7687

Max Act: 4.5094. Min Act: -0.0000

Data Index: 887323 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 6.7687. Min Range: -6.7687

Max Act: 4.1195. Min Act: -0.0000

Data Index: 725420 (C4 (Web Text))

Max Activating Token Index: 959

Text #16

Max Range: 6.7687. Min Range: -6.7687

Max Act: 4.2706. Min Act: -0.0000

Data Index: 254852 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 6.7687. Min Range: -6.7687

Max Act: 4.2462. Min Act: -0.0000

Data Index: 399396 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 6.7687. Min Range: -6.7687

Max Act: 4.4332. Min Act: -0.0000

Data Index: 1232272 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 6.7687. Min Range: -6.7687

Max Act: 4.3721. Min Act: -0.0000

Data Index: 843594 (C4 (Web Text))

Max Activating Token Index: 145