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

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

Neuron 500 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0572. Min Act: -0.0002

Data Index: 825619 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0555. Min Act: -0.0002

Data Index: 339557 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0547. Min Act: -0.0002

Data Index: 604826 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1055731 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0540. Min Act: -0.0002

Data Index: 1151728 (C4 (Web Text))

Max Activating Token Index: 324

Text #5

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0539. Min Act: -0.0002

Data Index: 1080657 (C4 (Web Text))

Max Activating Token Index: 504

Text #6

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0518. Min Act: -0.0002

Data Index: 806405 (C4 (Web Text))

Max Activating Token Index: 510

Text #7

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0533. Min Act: -0.0002

Data Index: 1074296 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0531. Min Act: -0.0002

Data Index: 377726 (C4 (Web Text))

Max Activating Token Index: 224

Text #9

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0532. Min Act: -0.0002

Data Index: 1055982 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0530. Min Act: -0.0002

Data Index: 705329 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0529. Min Act: -0.0002

Data Index: 636494 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0527. Min Act: -0.0002

Data Index: 1119219 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0526. Min Act: -0.0002

Data Index: 104972 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0525. Min Act: -0.0002

Data Index: 725884 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0525. Min Act: -0.0002

Data Index: 1492982 (Python Code)

Max Activating Token Index: 263

Text #16

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0525. Min Act: -0.0002

Data Index: 992339 (C4 (Web Text))

Max Activating Token Index: 614

Text #17

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0523. Min Act: -0.0002

Data Index: 159632 (C4 (Web Text))

Max Activating Token Index: 678

Text #18

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0523. Min Act: -0.0002

Data Index: 468044 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0522. Min Act: -0.0002

Data Index: 1031549 (C4 (Web Text))

Max Activating Token Index: 948