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

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

Neuron 968 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: 0.0743. Min Range: -0.0743

Max Act: 0.0738. Min Act: -0.0002

Data Index: 1274325 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0743. Min Act: -0.0002

Data Index: 778051 (C4 (Web Text))

Max Activating Token Index: 311

Text #2

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0708. Min Act: -0.0002

Data Index: 1330018 (C4 (Web Text))

Max Activating Token Index: 164

Text #3

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0587. Min Act: -0.0002

Data Index: 35068 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0474. Min Act: -0.0002

Data Index: 294764 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0526. Min Act: -0.0002

Data Index: 106760 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0591. Min Act: -0.0002

Data Index: 619600 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0654. Min Act: -0.0002

Data Index: 722200 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0516. Min Act: -0.0002

Data Index: 431222 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0548. Min Act: -0.0002

Data Index: 392447 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0558. Min Act: -0.0002

Data Index: 243395 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0559. Min Act: -0.0002

Data Index: 271919 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0533. Min Act: -0.0002

Data Index: 566998 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0493. Min Act: -0.0002

Data Index: 22211 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0566. Min Act: -0.0002

Data Index: 1355692 (C4 (Web Text))

Max Activating Token Index: 451

Text #15

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0541. Min Act: -0.0002

Data Index: 1038453 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0517. Min Act: -0.0002

Data Index: 382200 (C4 (Web Text))

Max Activating Token Index: 102

Text #17

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0545. Min Act: -0.0002

Data Index: 1263309 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0523. Min Act: -0.0002

Data Index: 705442 (C4 (Web Text))

Max Activating Token Index: 522

Text #19

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0525. Min Act: -0.0002

Data Index: 502047 (C4 (Web Text))

Max Activating Token Index: 535