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

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

Neuron 755 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5126. Min Range: -4.5126

Max Act: 4.2784. Min Act: -0.0000

Data Index: 1071085 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 4.5126. Min Range: -4.5126

Max Act: 4.5126. Min Act: -0.0000

Data Index: 1009024 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 4.5126. Min Range: -4.5126

Max Act: 3.5785. Min Act: -0.0000

Data Index: 1544584 (Python Code)

Max Activating Token Index: 994

Text #3

Max Range: 4.5126. Min Range: -4.5126

Max Act: 3.2703. Min Act: -0.0000

Data Index: 1318190 (C4 (Web Text))

Max Activating Token Index: 891

Text #4

Max Range: 4.5126. Min Range: -4.5126

Max Act: 3.2243. Min Act: -0.0000

Data Index: 815510 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 4.5126. Min Range: -4.5126

Max Act: 2.9326. Min Act: -0.0000

Data Index: 712862 (C4 (Web Text))

Max Activating Token Index: 819

Text #6

Max Range: 4.5126. Min Range: -4.5126

Max Act: 3.0870. Min Act: -0.0000

Data Index: 757353 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 4.5126. Min Range: -4.5126

Max Act: 3.0748. Min Act: -0.0000

Data Index: 1488541 (Python Code)

Max Activating Token Index: 699

Text #8

Max Range: 4.5126. Min Range: -4.5126

Max Act: 3.2123. Min Act: -0.0000

Data Index: 1522066 (Python Code)

Max Activating Token Index: 146

Text #9

Max Range: 4.5126. Min Range: -4.5126

Max Act: 3.0847. Min Act: -0.0000

Data Index: 906268 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 4.5126. Min Range: -4.5126

Max Act: 2.9752. Min Act: -0.0000

Data Index: 469353 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 4.5126. Min Range: -4.5126

Max Act: 3.2633. Min Act: -0.0000

Data Index: 1385237 (Python Code)

Max Activating Token Index: 475

Text #12

Max Range: 4.5126. Min Range: -4.5126

Max Act: 3.1236. Min Act: -0.0000

Data Index: 1072326 (C4 (Web Text))

Max Activating Token Index: 698

Text #13

Max Range: 4.5126. Min Range: -4.5126

Max Act: 3.1894. Min Act: -0.0000

Data Index: 387387 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 4.5126. Min Range: -4.5126

Max Act: 3.0072. Min Act: -0.0000

Data Index: 628937 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 4.5126. Min Range: -4.5126

Max Act: 2.6882. Min Act: -0.0000

Data Index: 1594282 (Python Code)

Max Activating Token Index: 638

Text #16

Max Range: 4.5126. Min Range: -4.5126

Max Act: 2.9432. Min Act: -0.0000

Data Index: 768263 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 4.5126. Min Range: -4.5126

Max Act: 2.9538. Min Act: -0.0000

Data Index: 819283 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 4.5126. Min Range: -4.5126

Max Act: 2.9501. Min Act: -0.0000

Data Index: 1394467 (Python Code)

Max Activating Token Index: 162

Text #19

Max Range: 4.5126. Min Range: -4.5126

Max Act: 2.7679. Min Act: -0.0000

Data Index: 746088 (C4 (Web Text))

Max Activating Token Index: 937