Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 75 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0643. Min Act: -0.0006

Data Index: 759556 (C4 (Web Text))

Max Activating Token Index: 685

Text #1

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0573. Min Act: -0.0006

Data Index: 91729 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0535. Min Act: -0.0006

Data Index: 220962 (C4 (Web Text))

Max Activating Token Index: 669

Text #3

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0510. Min Act: -0.0006

Data Index: 322536 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0556. Min Act: -0.0006

Data Index: 858708 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0550. Min Act: -0.0006

Data Index: 1063452 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0558. Min Act: -0.0006

Data Index: 210236 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0556. Min Act: -0.0006

Data Index: 1202222 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0527. Min Act: -0.0006

Data Index: 665394 (C4 (Web Text))

Max Activating Token Index: 572

Text #9

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0537. Min Act: -0.0006

Data Index: 228207 (C4 (Web Text))

Max Activating Token Index: 560

Text #10

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0486. Min Act: -0.0006

Data Index: 937765 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0548. Min Act: -0.0006

Data Index: 733144 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0568. Min Act: -0.0006

Data Index: 1211385 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0479. Min Act: -0.0006

Data Index: 1145739 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0469. Min Act: -0.0006

Data Index: 1212273 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0538. Min Act: -0.0006

Data Index: 1007201 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0525. Min Act: -0.0006

Data Index: 344232 (C4 (Web Text))

Max Activating Token Index: 358

Text #17

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0435. Min Act: -0.0006

Data Index: 493761 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0502. Min Act: -0.0006

Data Index: 1055165 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0498. Min Act: -0.0006

Data Index: 991889 (C4 (Web Text))

Max Activating Token Index: 157