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

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

Neuron 4212 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1315. Min Range: -3.1315

Max Act: 3.0459. Min Act: -0.0000

Data Index: 1133046 (C4 (Web Text))

Max Activating Token Index: 281

Text #1

Max Range: 3.1315. Min Range: -3.1315

Max Act: 3.1315. Min Act: -0.0000

Data Index: 276432 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 3.1315. Min Range: -3.1315

Max Act: 3.0786. Min Act: -0.0000

Data Index: 614884 (C4 (Web Text))

Max Activating Token Index: 325

Text #3

Max Range: 3.1315. Min Range: -3.1315

Max Act: 2.9682. Min Act: -0.0000

Data Index: 18583 (C4 (Web Text))

Max Activating Token Index: 570

Text #4

Max Range: 3.1315. Min Range: -3.1315

Max Act: 1.9001. Min Act: -0.0000

Data Index: 749401 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 3.1315. Min Range: -3.1315

Max Act: 2.0885. Min Act: -0.0000

Data Index: 55813 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 3.1315. Min Range: -3.1315

Max Act: 1.9091. Min Act: -0.0000

Data Index: 1316180 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 3.1315. Min Range: -3.1315

Max Act: 1.8844. Min Act: -0.0000

Data Index: 781949 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 3.1315. Min Range: -3.1315

Max Act: 1.8542. Min Act: -0.0000

Data Index: 995969 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 3.1315. Min Range: -3.1315

Max Act: 1.7592. Min Act: -0.0000

Data Index: 1024461 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 3.1315. Min Range: -3.1315

Max Act: 1.8181. Min Act: -0.0000

Data Index: 1170824 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 3.1315. Min Range: -3.1315

Max Act: 1.7753. Min Act: -0.0000

Data Index: 625616 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 3.1315. Min Range: -3.1315

Max Act: 1.6636. Min Act: -0.0000

Data Index: 854718 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 3.1315. Min Range: -3.1315

Max Act: 1.7362. Min Act: -0.0000

Data Index: 227785 (C4 (Web Text))

Max Activating Token Index: 837

Text #14

Max Range: 3.1315. Min Range: -3.1315

Max Act: 1.7202. Min Act: -0.0000

Data Index: 1233823 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 3.1315. Min Range: -3.1315

Max Act: 1.6092. Min Act: -0.0000

Data Index: 481835 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 3.1315. Min Range: -3.1315

Max Act: 1.5228. Min Act: -0.0000

Data Index: 291042 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 3.1315. Min Range: -3.1315

Max Act: 1.4755. Min Act: -0.0000

Data Index: 1116811 (C4 (Web Text))

Max Activating Token Index: 849

Text #18

Max Range: 3.1315. Min Range: -3.1315

Max Act: 1.4597. Min Act: -0.0000

Data Index: 295193 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 3.1315. Min Range: -3.1315

Max Act: 1.5381. Min Act: -0.0000

Data Index: 568752 (C4 (Web Text))

Max Activating Token Index: 396