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

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

Neuron 4852 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0614. Min Act: -0.0002

Data Index: 943962 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0584. Min Act: -0.0003

Data Index: 744404 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0555. Min Act: -0.0003

Data Index: 1061322 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0541. Min Act: -0.0002

Data Index: 168916 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0538. Min Act: -0.0002

Data Index: 956355 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0528. Min Act: -0.0003

Data Index: 470614 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0518. Min Act: -0.0002

Data Index: 739097 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0497. Min Act: -0.0003

Data Index: 1016503 (C4 (Web Text))

Max Activating Token Index: 878

Text #8

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0512. Min Act: -0.0003

Data Index: 50171 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0509. Min Act: -0.0003

Data Index: 738205 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0493. Min Act: -0.0003

Data Index: 838999 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0485. Min Act: -0.0002

Data Index: 233138 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0484. Min Act: -0.0002

Data Index: 188111 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0477. Min Act: -0.0002

Data Index: 1054747 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0472. Min Act: -0.0003

Data Index: 893023 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0466. Min Act: -0.0002

Data Index: 577672 (C4 (Web Text))

Max Activating Token Index: 589

Text #16

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0478. Min Act: -0.0002

Data Index: 993586 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0472. Min Act: -0.0003

Data Index: 94930 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0453. Min Act: -0.0003

Data Index: 777565 (C4 (Web Text))

Max Activating Token Index: 997

Text #19

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0469. Min Act: -0.0003

Data Index: 541551 (C4 (Web Text))

Max Activating Token Index: 832