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

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

Neuron 3535 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: 0.0675. Min Range: -0.0675

Max Act: 0.0675. Min Act: -0.0003

Data Index: 587063 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0546. Min Act: -0.0003

Data Index: 207911 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0518. Min Act: -0.0003

Data Index: 776603 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0516. Min Act: -0.0003

Data Index: 1029589 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0504. Min Act: -0.0003

Data Index: 796321 (C4 (Web Text))

Max Activating Token Index: 798

Text #5

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0517. Min Act: -0.0003

Data Index: 207715 (C4 (Web Text))

Max Activating Token Index: 419

Text #6

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0501. Min Act: -0.0003

Data Index: 96770 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0512. Min Act: -0.0002

Data Index: 466088 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0472. Min Act: -0.0003

Data Index: 753393 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0492. Min Act: -0.0003

Data Index: 1194115 (C4 (Web Text))

Max Activating Token Index: 338

Text #10

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0502. Min Act: -0.0003

Data Index: 22742 (C4 (Web Text))

Max Activating Token Index: 491

Text #11

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0489. Min Act: -0.0003

Data Index: 347633 (C4 (Web Text))

Max Activating Token Index: 872

Text #12

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0479. Min Act: -0.0003

Data Index: 377564 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0467. Min Act: -0.0003

Data Index: 1058591 (C4 (Web Text))

Max Activating Token Index: 385

Text #14

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0470. Min Act: -0.0003

Data Index: 323558 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0452. Min Act: -0.0003

Data Index: 1146452 (C4 (Web Text))

Max Activating Token Index: 526

Text #16

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0462. Min Act: -0.0003

Data Index: 706493 (C4 (Web Text))

Max Activating Token Index: 2

Text #17

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0454. Min Act: -0.0003

Data Index: 1016664 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0450. Min Act: -0.0002

Data Index: 181661 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0465. Min Act: -0.0003

Data Index: 967628 (C4 (Web Text))

Max Activating Token Index: 86