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

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

Neuron 3475 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: 0.0628. Min Range: -0.0628

Max Act: 0.0628. Min Act: -0.0002

Data Index: 58670 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0525. Min Act: -0.0002

Data Index: 556911 (C4 (Web Text))

Max Activating Token Index: 814

Text #2

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0543. Min Act: -0.0002

Data Index: 416951 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0520. Min Act: -0.0002

Data Index: 786336 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1260145 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0458. Min Act: -0.0002

Data Index: 353789 (C4 (Web Text))

Max Activating Token Index: 242

Text #6

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0444. Min Act: -0.0002

Data Index: 118659 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0457. Min Act: -0.0002

Data Index: 42112 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0454. Min Act: -0.0002

Data Index: 648064 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0453. Min Act: -0.0002

Data Index: 289048 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0434. Min Act: -0.0002

Data Index: 767379 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0433. Min Act: -0.0002

Data Index: 22068 (C4 (Web Text))

Max Activating Token Index: 691

Text #12

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0445. Min Act: -0.0002

Data Index: 1346139 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0423. Min Act: -0.0002

Data Index: 474242 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0425. Min Act: -0.0002

Data Index: 649034 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0428. Min Act: -0.0002

Data Index: 697354 (C4 (Web Text))

Max Activating Token Index: 599

Text #16

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0417. Min Act: -0.0002

Data Index: 1202341 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0407. Min Act: -0.0002

Data Index: 21568 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1097936 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 0.0628. Min Range: -0.0628

Max Act: 0.0408. Min Act: -0.0002

Data Index: 178905 (C4 (Web Text))

Max Activating Token Index: 336