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

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

Neuron 907 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: 0.0652. Min Range: -0.0652

Max Act: 0.0652. Min Act: -0.0002

Data Index: 430723 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0507. Min Act: -0.0003

Data Index: 204055 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0494. Min Act: -0.0003

Data Index: 859715 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0514. Min Act: -0.0003

Data Index: 72281 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0466. Min Act: -0.0003

Data Index: 50762 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0457. Min Act: -0.0002

Data Index: 215192 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0480. Min Act: -0.0003

Data Index: 499482 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0456. Min Act: -0.0003

Data Index: 842636 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0448. Min Act: -0.0003

Data Index: 372035 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0426. Min Act: -0.0003

Data Index: 297341 (C4 (Web Text))

Max Activating Token Index: 446

Text #10

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0432. Min Act: -0.0003

Data Index: 836139 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0427. Min Act: -0.0003

Data Index: 440264 (C4 (Web Text))

Max Activating Token Index: 815

Text #12

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0419. Min Act: -0.0003

Data Index: 172271 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0394. Min Act: -0.0002

Data Index: 814423 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0408. Min Act: -0.0003

Data Index: 495381 (C4 (Web Text))

Max Activating Token Index: 202

Text #15

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0403. Min Act: -0.0003

Data Index: 512376 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0410. Min Act: -0.0002

Data Index: 264578 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0418. Min Act: -0.0003

Data Index: 23227 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0417. Min Act: -0.0003

Data Index: 275913 (C4 (Web Text))

Max Activating Token Index: 486

Text #19

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0399. Min Act: -0.0002

Data Index: 136003 (C4 (Web Text))

Max Activating Token Index: 972