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

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

Neuron 1074 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1905. Min Act: -0.0001

Data Index: 971530 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1906. Min Act: -0.0001

Data Index: 1110934 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1758. Min Act: -0.0001

Data Index: 512619 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1839. Min Act: -0.0001

Data Index: 242226 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1646. Min Act: -0.0001

Data Index: 813629 (C4 (Web Text))

Max Activating Token Index: 828

Text #5

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1654. Min Act: -0.0001

Data Index: 443910 (C4 (Web Text))

Max Activating Token Index: 406

Text #6

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1430. Min Act: -0.0001

Data Index: 745522 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1865. Min Act: -0.0001

Data Index: 238718 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1612. Min Act: -0.0001

Data Index: 1070597 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1594. Min Act: -0.0001

Data Index: 841243 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1359. Min Act: -0.0001

Data Index: 587785 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1570. Min Act: -0.0001

Data Index: 1259129 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1629. Min Act: -0.0001

Data Index: 58219 (C4 (Web Text))

Max Activating Token Index: 916

Text #13

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1560. Min Act: -0.0001

Data Index: 405087 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1408. Min Act: -0.0001

Data Index: 418682 (C4 (Web Text))

Max Activating Token Index: 163

Text #15

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1596. Min Act: -0.0001

Data Index: 709853 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1544. Min Act: -0.0001

Data Index: 1076115 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1618. Min Act: -0.0001

Data Index: 1044265 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1598. Min Act: -0.0001

Data Index: 840504 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1392. Min Act: -0.0001

Data Index: 1109572 (C4 (Web Text))

Max Activating Token Index: 120