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

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

Neuron 4616 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: 0.0645. Min Range: -0.0645

Max Act: 0.0581. Min Act: -0.0002

Data Index: 1024058 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0601. Min Act: -0.0002

Data Index: 568387 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0645. Min Act: -0.0002

Data Index: 1309296 (C4 (Web Text))

Max Activating Token Index: 414

Text #3

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0506. Min Act: -0.0002

Data Index: 133563 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0585. Min Act: -0.0002

Data Index: 1617912 (Python Code)

Max Activating Token Index: 341

Text #5

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0597. Min Act: -0.0002

Data Index: 1518338 (Python Code)

Max Activating Token Index: 208

Text #6

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0602. Min Act: -0.0002

Data Index: 1156247 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0554. Min Act: -0.0002

Data Index: 1025117 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0602. Min Act: -0.0002

Data Index: 1067625 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0548. Min Act: -0.0002

Data Index: 1607604 (Python Code)

Max Activating Token Index: 265

Text #10

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0558. Min Act: -0.0002

Data Index: 922625 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0553. Min Act: -0.0002

Data Index: 59027 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0531. Min Act: -0.0002

Data Index: 1450513 (Python Code)

Max Activating Token Index: 344

Text #13

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0537. Min Act: -0.0002

Data Index: 138558 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0530. Min Act: -0.0002

Data Index: 1538265 (Python Code)

Max Activating Token Index: 459

Text #15

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0505. Min Act: -0.0002

Data Index: 343048 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0522. Min Act: -0.0002

Data Index: 1635194 (Python Code)

Max Activating Token Index: 404

Text #17

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0541. Min Act: -0.0002

Data Index: 1492447 (Python Code)

Max Activating Token Index: 608

Text #18

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0556. Min Act: -0.0002

Data Index: 1421557 (Python Code)

Max Activating Token Index: 21

Text #19

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0506. Min Act: -0.0002

Data Index: 507339 (C4 (Web Text))

Max Activating Token Index: 98