Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 190 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0593. Min Act: -0.0003

Data Index: 768837 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0588. Min Act: -0.0002

Data Index: 132054 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0570. Min Act: -0.0003

Data Index: 516734 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0556. Min Act: -0.0002

Data Index: 60387 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0562. Min Act: -0.0003

Data Index: 1224747 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0562. Min Act: -0.0002

Data Index: 1129985 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0557. Min Act: -0.0003

Data Index: 1010728 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0552. Min Act: -0.0003

Data Index: 991121 (C4 (Web Text))

Max Activating Token Index: 736

Text #8

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0526. Min Act: -0.0004

Data Index: 827216 (C4 (Web Text))

Max Activating Token Index: 316

Text #9

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0525. Min Act: -0.0003

Data Index: 4664 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0510. Min Act: -0.0003

Data Index: 238547 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0509. Min Act: -0.0003

Data Index: 289659 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0509. Min Act: -0.0003

Data Index: 1209657 (C4 (Web Text))

Max Activating Token Index: 187

Text #13

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0524. Min Act: -0.0003

Data Index: 314880 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0528. Min Act: -0.0003

Data Index: 1082685 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0529. Min Act: -0.0003

Data Index: 815318 (C4 (Web Text))

Max Activating Token Index: 336

Text #16

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0505. Min Act: -0.0003

Data Index: 452797 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0488. Min Act: -0.0003

Data Index: 325286 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0500. Min Act: -0.0002

Data Index: 874396 (C4 (Web Text))

Max Activating Token Index: 714

Text #19

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0468. Min Act: -0.0003

Data Index: 17780 (C4 (Web Text))

Max Activating Token Index: 807