Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3982 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0669. Min Act: -0.0002

Data Index: 757619 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0578. Min Act: -0.0002

Data Index: 1089637 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0571. Min Act: -0.0002

Data Index: 67876 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0501. Min Act: -0.0002

Data Index: 154026 (C4 (Web Text))

Max Activating Token Index: 456

Text #4

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0536. Min Act: -0.0002

Data Index: 150939 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0509. Min Act: -0.0002

Data Index: 873916 (C4 (Web Text))

Max Activating Token Index: 549

Text #6

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0514. Min Act: -0.0002

Data Index: 731454 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0483. Min Act: -0.0002

Data Index: 68233 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0479. Min Act: -0.0002

Data Index: 895154 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0472. Min Act: -0.0002

Data Index: 373988 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0478. Min Act: -0.0002

Data Index: 631273 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0482. Min Act: -0.0002

Data Index: 876406 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0462. Min Act: -0.0002

Data Index: 1319771 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0431. Min Act: -0.0002

Data Index: 826052 (C4 (Web Text))

Max Activating Token Index: 144

Text #14

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0446. Min Act: -0.0002

Data Index: 338900 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0441. Min Act: -0.0002

Data Index: 811544 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0449. Min Act: -0.0002

Data Index: 1332255 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0466. Min Act: -0.0002

Data Index: 586944 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0427. Min Act: -0.0002

Data Index: 683622 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0410. Min Act: -0.0002

Data Index: 783436 (C4 (Web Text))

Max Activating Token Index: 533