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

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

Neuron 1496 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.6257. Min Range: -7.6257

Max Act: 7.6257. Min Act: -0.0000

Data Index: 193758 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 7.6257. Min Range: -7.6257

Max Act: 6.0630. Min Act: -0.0000

Data Index: 817674 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 7.6257. Min Range: -7.6257

Max Act: 6.3614. Min Act: -0.0000

Data Index: 1233406 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 7.6257. Min Range: -7.6257

Max Act: 5.2737. Min Act: -0.0000

Data Index: 224775 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 7.6257. Min Range: -7.6257

Max Act: 4.4995. Min Act: -0.0000

Data Index: 1202399 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 7.6257. Min Range: -7.6257

Max Act: 4.8282. Min Act: -0.0000

Data Index: 162941 (C4 (Web Text))

Max Activating Token Index: 291

Text #6

Max Range: 7.6257. Min Range: -7.6257

Max Act: 4.4724. Min Act: -0.0000

Data Index: 123006 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 7.6257. Min Range: -7.6257

Max Act: 4.2128. Min Act: -0.0000

Data Index: 556559 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 7.6257. Min Range: -7.6257

Max Act: 4.1821. Min Act: -0.0000

Data Index: 37040 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 7.6257. Min Range: -7.6257

Max Act: 4.0073. Min Act: -0.0000

Data Index: 419133 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 7.6257. Min Range: -7.6257

Max Act: 4.3452. Min Act: -0.0000

Data Index: 196781 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 7.6257. Min Range: -7.6257

Max Act: 4.1389. Min Act: -0.0000

Data Index: 784477 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 7.6257. Min Range: -7.6257

Max Act: 3.8781. Min Act: -0.0000

Data Index: 11683 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 7.6257. Min Range: -7.6257

Max Act: 4.1569. Min Act: -0.0000

Data Index: 1046520 (C4 (Web Text))

Max Activating Token Index: 144

Text #14

Max Range: 7.6257. Min Range: -7.6257

Max Act: 3.9812. Min Act: -0.0000

Data Index: 169661 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 7.6257. Min Range: -7.6257

Max Act: 4.2628. Min Act: -0.0000

Data Index: 905483 (C4 (Web Text))

Max Activating Token Index: 875

Text #16

Max Range: 7.6257. Min Range: -7.6257

Max Act: 3.6013. Min Act: -0.0000

Data Index: 70264 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 7.6257. Min Range: -7.6257

Max Act: 3.7970. Min Act: -0.0000

Data Index: 1307798 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 7.6257. Min Range: -7.6257

Max Act: 3.9417. Min Act: -0.0000

Data Index: 1174387 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 7.6257. Min Range: -7.6257

Max Act: 3.9241. Min Act: -0.0000

Data Index: 300435 (C4 (Web Text))

Max Activating Token Index: 42