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

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

Neuron 1466 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0914. Min Act: -0.0002

Data Index: 1114123 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0948. Min Act: -0.0002

Data Index: 1288372 (C4 (Web Text))

Max Activating Token Index: 313

Text #2

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0781. Min Act: -0.0002

Data Index: 170003 (C4 (Web Text))

Max Activating Token Index: 517

Text #3

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0735. Min Act: -0.0002

Data Index: 387842 (C4 (Web Text))

Max Activating Token Index: 474

Text #4

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0750. Min Act: -0.0002

Data Index: 326513 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0613. Min Act: -0.0002

Data Index: 175701 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0620. Min Act: -0.0002

Data Index: 219914 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0542. Min Act: -0.0002

Data Index: 584487 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0529. Min Act: -0.0002

Data Index: 354749 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0515. Min Act: -0.0002

Data Index: 1164400 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0532. Min Act: -0.0002

Data Index: 94357 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0495. Min Act: -0.0002

Data Index: 636622 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0515. Min Act: -0.0002

Data Index: 480110 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0549. Min Act: -0.0002

Data Index: 464606 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0487. Min Act: -0.0002

Data Index: 979541 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0508. Min Act: -0.0002

Data Index: 784956 (C4 (Web Text))

Max Activating Token Index: 1022

Text #16

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0502. Min Act: -0.0002

Data Index: 187569 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0485. Min Act: -0.0002

Data Index: 836627 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0450. Min Act: -0.0002

Data Index: 313455 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0438. Min Act: -0.0002

Data Index: 216790 (C4 (Web Text))

Max Activating Token Index: 183