Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2117 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.2215. Min Act: -0.0001

Data Index: 878397 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1860. Min Act: -0.0001

Data Index: 265250 (C4 (Web Text))

Max Activating Token Index: 519

Text #2

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1881. Min Act: -0.0001

Data Index: 1326029 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1759. Min Act: -0.0001

Data Index: 851156 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1609. Min Act: -0.0001

Data Index: 122456 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1714. Min Act: -0.0001

Data Index: 627767 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1707. Min Act: -0.0001

Data Index: 109960 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1682. Min Act: -0.0001

Data Index: 1346002 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1640. Min Act: -0.0001

Data Index: 662310 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1653. Min Act: -0.0001

Data Index: 898859 (C4 (Web Text))

Max Activating Token Index: 814

Text #10

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1703. Min Act: -0.0001

Data Index: 939781 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1643. Min Act: -0.0001

Data Index: 961905 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1680. Min Act: -0.0001

Data Index: 25508 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1612. Min Act: -0.0001

Data Index: 372738 (C4 (Web Text))

Max Activating Token Index: 284

Text #14

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1619. Min Act: -0.0001

Data Index: 225039 (C4 (Web Text))

Max Activating Token Index: 279

Text #15

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1635. Min Act: -0.0001

Data Index: 1213057 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1580. Min Act: -0.0001

Data Index: 1111589 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1629. Min Act: -0.0001

Data Index: 73547 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1605. Min Act: -0.0001

Data Index: 1257200 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1600. Min Act: -0.0001

Data Index: 449249 (C4 (Web Text))

Max Activating Token Index: 559