Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 2024 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1819. Min Act: -0.0003

Data Index: 561899 (C4 (Web Text))

Max Activating Token Index: 340

Text #1

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1799. Min Act: -0.0003

Data Index: 914028 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1689. Min Act: -0.0003

Data Index: 1182869 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1687. Min Act: -0.0003

Data Index: 1273278 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1601. Min Act: -0.0003

Data Index: 1047920 (C4 (Web Text))

Max Activating Token Index: 307

Text #5

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1501. Min Act: -0.0003

Data Index: 1248184 (C4 (Web Text))

Max Activating Token Index: 576

Text #6

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1614. Min Act: -0.0003

Data Index: 1318103 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1595. Min Act: -0.0003

Data Index: 507736 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1516. Min Act: -0.0004

Data Index: 206035 (C4 (Web Text))

Max Activating Token Index: 330

Text #9

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1548. Min Act: -0.0003

Data Index: 931482 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1499. Min Act: -0.0003

Data Index: 843737 (C4 (Web Text))

Max Activating Token Index: 524

Text #11

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1551. Min Act: -0.0003

Data Index: 1123493 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1424. Min Act: -0.0004

Data Index: 1206679 (C4 (Web Text))

Max Activating Token Index: 698

Text #13

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1509. Min Act: -0.0003

Data Index: 969654 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1520. Min Act: -0.0003

Data Index: 800175 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1454. Min Act: -0.0003

Data Index: 651001 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1382. Min Act: -0.0003

Data Index: 767494 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1483. Min Act: -0.0002

Data Index: 658380 (C4 (Web Text))

Max Activating Token Index: 768

Text #18

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1407. Min Act: -0.0003

Data Index: 1133274 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 0.1819. Min Range: -0.1819

Max Act: 0.1536. Min Act: -0.0003

Data Index: 1048881 (C4 (Web Text))

Max Activating Token Index: 507