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

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

Neuron 4346 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7889. Min Range: -1.7889

Max Act: 1.7889. Min Act: -0.0000

Data Index: 1304442 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 1.7889. Min Range: -1.7889

Max Act: 1.5573. Min Act: -0.0000

Data Index: 773536 (C4 (Web Text))

Max Activating Token Index: 437

Text #2

Max Range: 1.7889. Min Range: -1.7889

Max Act: 1.5695. Min Act: -0.0000

Data Index: 297617 (C4 (Web Text))

Max Activating Token Index: 938

Text #3

Max Range: 1.7889. Min Range: -1.7889

Max Act: 1.5390. Min Act: -0.0000

Data Index: 1178382 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 1.7889. Min Range: -1.7889

Max Act: 1.5501. Min Act: -0.0000

Data Index: 212116 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 1.7889. Min Range: -1.7889

Max Act: 1.5425. Min Act: -0.0000

Data Index: 105550 (C4 (Web Text))

Max Activating Token Index: 917

Text #6

Max Range: 1.7889. Min Range: -1.7889

Max Act: 1.5309. Min Act: -0.0000

Data Index: 653844 (C4 (Web Text))

Max Activating Token Index: 542

Text #7

Max Range: 1.7889. Min Range: -1.7889

Max Act: 1.4404. Min Act: -0.0000

Data Index: 514862 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 1.7889. Min Range: -1.7889

Max Act: 1.5423. Min Act: -0.0000

Data Index: 328647 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 1.7889. Min Range: -1.7889

Max Act: 1.4416. Min Act: -0.0000

Data Index: 1355991 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 1.7889. Min Range: -1.7889

Max Act: 1.5124. Min Act: -0.0000

Data Index: 1213864 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 1.7889. Min Range: -1.7889

Max Act: 1.5687. Min Act: -0.0000

Data Index: 393974 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 1.7889. Min Range: -1.7889

Max Act: 1.4815. Min Act: -0.0000

Data Index: 635093 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 1.7889. Min Range: -1.7889

Max Act: 1.5478. Min Act: -0.0000

Data Index: 1259975 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 1.7889. Min Range: -1.7889

Max Act: 1.4619. Min Act: -0.0000

Data Index: 1221072 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 1.7889. Min Range: -1.7889

Max Act: 1.5550. Min Act: -0.0000

Data Index: 305224 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 1.7889. Min Range: -1.7889

Max Act: 1.4568. Min Act: -0.0000

Data Index: 858541 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 1.7889. Min Range: -1.7889

Max Act: 1.4278. Min Act: -0.0000

Data Index: 682446 (C4 (Web Text))

Max Activating Token Index: 483

Text #18

Max Range: 1.7889. Min Range: -1.7889

Max Act: 1.4336. Min Act: -0.0000

Data Index: 71888 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 1.7889. Min Range: -1.7889

Max Act: 1.4371. Min Act: -0.0000

Data Index: 957457 (C4 (Web Text))

Max Activating Token Index: 740