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

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

Neuron 4835 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1419. Min Range: -1.1419

Max Act: 1.1419. Min Act: -0.0001

Data Index: 613584 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 1.1419. Min Range: -1.1419

Max Act: 1.0822. Min Act: -0.0001

Data Index: 1336589 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 1.1419. Min Range: -1.1419

Max Act: 1.0869. Min Act: -0.0001

Data Index: 964755 (C4 (Web Text))

Max Activating Token Index: 845

Text #3

Max Range: 1.1419. Min Range: -1.1419

Max Act: 0.8869. Min Act: -0.0001

Data Index: 1274279 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 1.1419. Min Range: -1.1419

Max Act: 0.8782. Min Act: -0.0001

Data Index: 60110 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 1.1419. Min Range: -1.1419

Max Act: 0.8264. Min Act: -0.0001

Data Index: 1304740 (C4 (Web Text))

Max Activating Token Index: 948

Text #6

Max Range: 1.1419. Min Range: -1.1419

Max Act: 0.8182. Min Act: -0.0001

Data Index: 686658 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 1.1419. Min Range: -1.1419

Max Act: 0.8420. Min Act: -0.0001

Data Index: 1043337 (C4 (Web Text))

Max Activating Token Index: 451

Text #8

Max Range: 1.1419. Min Range: -1.1419

Max Act: 0.8264. Min Act: -0.0001

Data Index: 634091 (C4 (Web Text))

Max Activating Token Index: 811

Text #9

Max Range: 1.1419. Min Range: -1.1419

Max Act: 0.7820. Min Act: -0.0001

Data Index: 902824 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 1.1419. Min Range: -1.1419

Max Act: 0.8627. Min Act: -0.0001

Data Index: 353424 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 1.1419. Min Range: -1.1419

Max Act: 0.8602. Min Act: -0.0001

Data Index: 181223 (C4 (Web Text))

Max Activating Token Index: 668

Text #12

Max Range: 1.1419. Min Range: -1.1419

Max Act: 0.8098. Min Act: -0.0001

Data Index: 649308 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 1.1419. Min Range: -1.1419

Max Act: 0.8039. Min Act: -0.0001

Data Index: 189323 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 1.1419. Min Range: -1.1419

Max Act: 0.8017. Min Act: -0.0001

Data Index: 429447 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 1.1419. Min Range: -1.1419

Max Act: 0.7878. Min Act: -0.0001

Data Index: 1281506 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 1.1419. Min Range: -1.1419

Max Act: 0.8076. Min Act: -0.0001

Data Index: 942521 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 1.1419. Min Range: -1.1419

Max Act: 0.7686. Min Act: -0.0001

Data Index: 620756 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 1.1419. Min Range: -1.1419

Max Act: 0.7645. Min Act: -0.0001

Data Index: 571478 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 1.1419. Min Range: -1.1419

Max Act: 0.7374. Min Act: -0.0001

Data Index: 200504 (C4 (Web Text))

Max Activating Token Index: 1007