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

Dataset: The Pile

Neuron 1073 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4086. Min Range: -1.4086

Max Act: 1.4086. Min Act: -0.0000

Data Index: 489964 (The Pile)

Max Activating Token Index: 648

Text #1

Max Range: 1.4086. Min Range: -1.4086

Max Act: 1.1428. Min Act: -0.0000

Data Index: 852992 (The Pile)

Max Activating Token Index: 725

Text #2

Max Range: 1.4086. Min Range: -1.4086

Max Act: 0.9549. Min Act: -0.0000

Data Index: 584790 (The Pile)

Max Activating Token Index: 406

Text #3

Max Range: 1.4086. Min Range: -1.4086

Max Act: 0.9451. Min Act: -0.0000

Data Index: 1348213 (The Pile)

Max Activating Token Index: 773

Text #4

Max Range: 1.4086. Min Range: -1.4086

Max Act: 0.9018. Min Act: -0.0000

Data Index: 801617 (The Pile)

Max Activating Token Index: 524

Text #5

Max Range: 1.4086. Min Range: -1.4086

Max Act: 0.9211. Min Act: -0.0000

Data Index: 447873 (The Pile)

Max Activating Token Index: 835

Text #6

Max Range: 1.4086. Min Range: -1.4086

Max Act: 0.7793. Min Act: -0.0000

Data Index: 969219 (The Pile)

Max Activating Token Index: 877

Text #7

Max Range: 1.4086. Min Range: -1.4086

Max Act: 0.8788. Min Act: -0.0000

Data Index: 1269919 (The Pile)

Max Activating Token Index: 461

Text #8

Max Range: 1.4086. Min Range: -1.4086

Max Act: 0.8695. Min Act: -0.0000

Data Index: 317110 (The Pile)

Max Activating Token Index: 514

Text #9

Max Range: 1.4086. Min Range: -1.4086

Max Act: 0.8469. Min Act: -0.0000

Data Index: 1482983 (The Pile)

Max Activating Token Index: 982

Text #10

Max Range: 1.4086. Min Range: -1.4086

Max Act: 0.7485. Min Act: -0.0000

Data Index: 1346700 (The Pile)

Max Activating Token Index: 90

Text #11

Max Range: 1.4086. Min Range: -1.4086

Max Act: 0.8425. Min Act: -0.0000

Data Index: 1488411 (The Pile)

Max Activating Token Index: 600

Text #12

Max Range: 1.4086. Min Range: -1.4086

Max Act: 0.8722. Min Act: -0.0000

Data Index: 1769092 (The Pile)

Max Activating Token Index: 109

Text #13

Max Range: 1.4086. Min Range: -1.4086

Max Act: 0.7688. Min Act: -0.0000

Data Index: 1042725 (The Pile)

Max Activating Token Index: 914

Text #14

Max Range: 1.4086. Min Range: -1.4086

Max Act: 0.8173. Min Act: -0.0000

Data Index: 1442845 (The Pile)

Max Activating Token Index: 511

Text #15

Max Range: 1.4086. Min Range: -1.4086

Max Act: 0.8253. Min Act: -0.0000

Data Index: 1742006 (The Pile)

Max Activating Token Index: 495

Text #16

Max Range: 1.4086. Min Range: -1.4086

Max Act: 0.8248. Min Act: -0.0000

Data Index: 28597 (The Pile)

Max Activating Token Index: 17

Text #17

Max Range: 1.4086. Min Range: -1.4086

Max Act: 0.7417. Min Act: -0.0000

Data Index: 682990 (The Pile)

Max Activating Token Index: 171

Text #18

Max Range: 1.4086. Min Range: -1.4086

Max Act: 0.7497. Min Act: -0.0000

Data Index: 383058 (The Pile)

Max Activating Token Index: 592

Text #19

Max Range: 1.4086. Min Range: -1.4086

Max Act: 0.8413. Min Act: -0.0000

Data Index: 869885 (The Pile)

Max Activating Token Index: 348