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

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

Neuron 1235 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0538. Min Act: -0.0002

Data Index: 858173 (C4 (Web Text))

Max Activating Token Index: 854

Text #1

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0549. Min Act: -0.0002

Data Index: 680548 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1118593 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0541. Min Act: -0.0002

Data Index: 1157755 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0534. Min Act: -0.0002

Data Index: 23328 (C4 (Web Text))

Max Activating Token Index: 592

Text #5

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0507. Min Act: -0.0002

Data Index: 1116743 (C4 (Web Text))

Max Activating Token Index: 623

Text #6

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1018081 (C4 (Web Text))

Max Activating Token Index: 986

Text #7

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0514. Min Act: -0.0002

Data Index: 604729 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0494. Min Act: -0.0002

Data Index: 226664 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0486. Min Act: -0.0002

Data Index: 1252456 (C4 (Web Text))

Max Activating Token Index: 692

Text #10

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0502. Min Act: -0.0002

Data Index: 776025 (C4 (Web Text))

Max Activating Token Index: 475

Text #11

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0505. Min Act: -0.0002

Data Index: 571405 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0482. Min Act: -0.0002

Data Index: 973062 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0501. Min Act: -0.0002

Data Index: 443981 (C4 (Web Text))

Max Activating Token Index: 733

Text #14

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0515. Min Act: -0.0002

Data Index: 719249 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0495. Min Act: -0.0002

Data Index: 490014 (C4 (Web Text))

Max Activating Token Index: 793

Text #16

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0513. Min Act: -0.0002

Data Index: 842279 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0468. Min Act: -0.0002

Data Index: 1042203 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0490. Min Act: -0.0002

Data Index: 699203 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0488. Min Act: -0.0002

Data Index: 939822 (C4 (Web Text))

Max Activating Token Index: 714