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

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

Neuron 2409 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.1569. Min Act: -0.0000

Data Index: 788 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0906. Min Act: -0.0000

Data Index: 707416 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0868. Min Act: -0.0000

Data Index: 1339827 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.1318. Min Act: -0.0000

Data Index: 418500 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0938. Min Act: -0.0000

Data Index: 258126 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0114. Min Act: -0.0000

Data Index: 268835 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 1.1569. Min Range: -1.1569

Max Act: 0.9734. Min Act: -0.0000

Data Index: 364476 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0435. Min Act: -0.0000

Data Index: 2817 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0467. Min Act: -0.0000

Data Index: 6542 (C4 (Web Text))

Max Activating Token Index: 193

Text #9

Max Range: 1.1569. Min Range: -1.1569

Max Act: 0.9963. Min Act: -0.0000

Data Index: 1084654 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0263. Min Act: -0.0000

Data Index: 1011284 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 1.1569. Min Range: -1.1569

Max Act: 0.9767. Min Act: -0.0000

Data Index: 1315574 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 1.1569. Min Range: -1.1569

Max Act: 1.0086. Min Act: -0.0000

Data Index: 1197361 (C4 (Web Text))

Max Activating Token Index: 216

Text #13

Max Range: 1.1569. Min Range: -1.1569

Max Act: 0.9646. Min Act: -0.0000

Data Index: 833787 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 1.1569. Min Range: -1.1569

Max Act: 0.9489. Min Act: -0.0000

Data Index: 791964 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 1.1569. Min Range: -1.1569

Max Act: 0.9224. Min Act: -0.0000

Data Index: 1114686 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 1.1569. Min Range: -1.1569

Max Act: 0.9694. Min Act: -0.0000

Data Index: 891377 (C4 (Web Text))

Max Activating Token Index: 99

Text #17

Max Range: 1.1569. Min Range: -1.1569

Max Act: 0.9436. Min Act: -0.0000

Data Index: 51167 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 1.1569. Min Range: -1.1569

Max Act: 0.9173. Min Act: -0.0000

Data Index: 986438 (C4 (Web Text))

Max Activating Token Index: 831

Text #19

Max Range: 1.1569. Min Range: -1.1569

Max Act: 0.8525. Min Act: -0.0000

Data Index: 62896 (C4 (Web Text))

Max Activating Token Index: 271