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

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

Neuron 4543 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.2152. Min Act: -0.0002

Data Index: 429046 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1740. Min Act: -0.0002

Data Index: 249465 (C4 (Web Text))

Max Activating Token Index: 451

Text #2

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1558. Min Act: -0.0002

Data Index: 934481 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1820. Min Act: -0.0002

Data Index: 1339313 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1640. Min Act: -0.0002

Data Index: 85556 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1321. Min Act: -0.0002

Data Index: 718393 (C4 (Web Text))

Max Activating Token Index: 133

Text #6

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1572. Min Act: -0.0002

Data Index: 965616 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1461. Min Act: -0.0002

Data Index: 1090729 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1505. Min Act: -0.0002

Data Index: 1208480 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1605. Min Act: -0.0002

Data Index: 1128938 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1688. Min Act: -0.0002

Data Index: 905074 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1574. Min Act: -0.0002

Data Index: 987209 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1551. Min Act: -0.0002

Data Index: 1117820 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1573. Min Act: -0.0002

Data Index: 232937 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1656. Min Act: -0.0002

Data Index: 469100 (C4 (Web Text))

Max Activating Token Index: 377

Text #15

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1603. Min Act: -0.0002

Data Index: 576085 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1647. Min Act: -0.0002

Data Index: 254564 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1589. Min Act: -0.0002

Data Index: 929530 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1632. Min Act: -0.0002

Data Index: 733981 (C4 (Web Text))

Max Activating Token Index: 734

Text #19

Max Range: 0.2152. Min Range: -0.2152

Max Act: 0.1460. Min Act: -0.0002

Data Index: 1496199 (Python Code)

Max Activating Token Index: 675