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

Dataset: The Pile

Neuron 804 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.4776. Min Act: -0.0000

Data Index: 854199 (The Pile)

Max Activating Token Index: 680

Text #1

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.3877. Min Act: -0.0000

Data Index: 1465873 (The Pile)

Max Activating Token Index: 279

Text #2

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.3426. Min Act: -0.0000

Data Index: 477016 (The Pile)

Max Activating Token Index: 545

Text #3

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.3058. Min Act: -0.0000

Data Index: 4771 (The Pile)

Max Activating Token Index: 614

Text #4

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.2952. Min Act: -0.0000

Data Index: 429593 (The Pile)

Max Activating Token Index: 52

Text #5

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.2611. Min Act: -0.0000

Data Index: 1303990 (The Pile)

Max Activating Token Index: 536

Text #6

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.2013. Min Act: -0.0000

Data Index: 966133 (The Pile)

Max Activating Token Index: 1000

Text #7

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.1762. Min Act: -0.0000

Data Index: 1241438 (The Pile)

Max Activating Token Index: 79

Text #8

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.1511. Min Act: -0.0000

Data Index: 250192 (The Pile)

Max Activating Token Index: 140

Text #9

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.1671. Min Act: -0.0000

Data Index: 812364 (The Pile)

Max Activating Token Index: 796

Text #10

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.1415. Min Act: -0.0000

Data Index: 62261 (The Pile)

Max Activating Token Index: 138

Text #11

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.1369. Min Act: -0.0000

Data Index: 1316098 (The Pile)

Max Activating Token Index: 562

Text #12

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.1206. Min Act: -0.0000

Data Index: 1953536 (The Pile)

Max Activating Token Index: 503

Text #13

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.1110. Min Act: -0.0000

Data Index: 1249918 (The Pile)

Max Activating Token Index: 563

Text #14

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.1630. Min Act: -0.0000

Data Index: 1163506 (The Pile)

Max Activating Token Index: 696

Text #15

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.0629. Min Act: -0.0000

Data Index: 1999083 (The Pile)

Max Activating Token Index: 712

Text #16

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.0727. Min Act: -0.0000

Data Index: 325074 (The Pile)

Max Activating Token Index: 381

Text #17

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.0674. Min Act: -0.0000

Data Index: 1918988 (The Pile)

Max Activating Token Index: 420

Text #18

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.1346. Min Act: -0.0000

Data Index: 296309 (The Pile)

Max Activating Token Index: 474

Text #19

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.0555. Min Act: -0.0000

Data Index: 1182952 (The Pile)

Max Activating Token Index: 506