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

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

Neuron 5027 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: 0.0587. Min Range: -0.0587

Max Act: 0.0586. Min Act: -0.0003

Data Index: 231341 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0587. Min Act: -0.0003

Data Index: 1284732 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0560. Min Act: -0.0002

Data Index: 45551 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0563. Min Act: -0.0003

Data Index: 891377 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0539. Min Act: -0.0003

Data Index: 1315574 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0576. Min Act: -0.0002

Data Index: 270336 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0539. Min Act: -0.0003

Data Index: 546363 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0536. Min Act: -0.0003

Data Index: 736969 (C4 (Web Text))

Max Activating Token Index: 861

Text #8

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0544. Min Act: -0.0003

Data Index: 619717 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0523. Min Act: -0.0003

Data Index: 861397 (C4 (Web Text))

Max Activating Token Index: 754

Text #10

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0543. Min Act: -0.0003

Data Index: 994804 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0514. Min Act: -0.0003

Data Index: 1104090 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0517. Min Act: -0.0003

Data Index: 862820 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0518. Min Act: -0.0003

Data Index: 390558 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0511. Min Act: -0.0003

Data Index: 743283 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0500. Min Act: -0.0003

Data Index: 774684 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0505. Min Act: -0.0003

Data Index: 582549 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0508. Min Act: -0.0002

Data Index: 1276537 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0503. Min Act: -0.0003

Data Index: 1203266 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 0.0587. Min Range: -0.0587

Max Act: 0.0493. Min Act: -0.0003

Data Index: 62896 (C4 (Web Text))

Max Activating Token Index: 200