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

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

Neuron 1426 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: 1.3536. Min Range: -1.3536

Max Act: 1.2842. Min Act: -0.0001

Data Index: 461925 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.3536. Min Act: -0.0001

Data Index: 567869 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1456. Min Act: -0.0001

Data Index: 691815 (C4 (Web Text))

Max Activating Token Index: 658

Text #3

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1831. Min Act: -0.0001

Data Index: 1054726 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1533. Min Act: -0.0001

Data Index: 750565 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1367. Min Act: -0.0001

Data Index: 636783 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1250. Min Act: -0.0001

Data Index: 80902 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1157. Min Act: -0.0001

Data Index: 1371805 (Python Code)

Max Activating Token Index: 941

Text #8

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1101. Min Act: -0.0001

Data Index: 778083 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1839. Min Act: -0.0001

Data Index: 966090 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1505. Min Act: -0.0001

Data Index: 539397 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1709. Min Act: -0.0001

Data Index: 1064708 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1898. Min Act: -0.0001

Data Index: 1261883 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1092. Min Act: -0.0001

Data Index: 514497 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1083. Min Act: -0.0001

Data Index: 362249 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.3020. Min Act: -0.0001

Data Index: 999451 (C4 (Web Text))

Max Activating Token Index: 633

Text #16

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.0971. Min Act: -0.0001

Data Index: 692207 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.0963. Min Act: -0.0001

Data Index: 1487 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1424. Min Act: -0.0001

Data Index: 833055 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 1.3536. Min Range: -1.3536

Max Act: 1.1112. Min Act: -0.0001

Data Index: 352406 (C4 (Web Text))

Max Activating Token Index: 869