Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3262 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.2516. Min Act: -0.0002

Data Index: 1049450 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.2317. Min Act: -0.0003

Data Index: 185643 (C4 (Web Text))

Max Activating Token Index: 592

Text #2

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.2160. Min Act: -0.0002

Data Index: 358509 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.2073. Min Act: -0.0003

Data Index: 501377 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1709. Min Act: -0.0003

Data Index: 606105 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1608. Min Act: -0.0003

Data Index: 982456 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1540. Min Act: -0.0003

Data Index: 662980 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1610. Min Act: -0.0002

Data Index: 991648 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1507. Min Act: -0.0002

Data Index: 53654 (C4 (Web Text))

Max Activating Token Index: 670

Text #9

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1496. Min Act: -0.0002

Data Index: 86475 (C4 (Web Text))

Max Activating Token Index: 403

Text #10

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1495. Min Act: -0.0002

Data Index: 400995 (C4 (Web Text))

Max Activating Token Index: 234

Text #11

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1480. Min Act: -0.0003

Data Index: 824915 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1454. Min Act: -0.0003

Data Index: 1298260 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1453. Min Act: -0.0003

Data Index: 624270 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1438. Min Act: -0.0003

Data Index: 570112 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1397. Min Act: -0.0002

Data Index: 381486 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1393. Min Act: -0.0002

Data Index: 668889 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1364. Min Act: -0.0003

Data Index: 979773 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1337. Min Act: -0.0003

Data Index: 72767 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1322. Min Act: -0.0003

Data Index: 843454 (C4 (Web Text))

Max Activating Token Index: 332