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

Dataset: The Pile

Neuron 982 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2494. Min Act: -0.0000

Data Index: 681805 (The Pile)

Max Activating Token Index: 776

Text #1

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2722. Min Act: -0.0000

Data Index: 325986 (The Pile)

Max Activating Token Index: 93

Text #2

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2973. Min Act: -0.0000

Data Index: 1071393 (The Pile)

Max Activating Token Index: 947

Text #3

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2755. Min Act: -0.0000

Data Index: 264719 (The Pile)

Max Activating Token Index: 65

Text #4

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2534. Min Act: -0.0000

Data Index: 477696 (The Pile)

Max Activating Token Index: 651

Text #5

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2519. Min Act: -0.0000

Data Index: 302113 (The Pile)

Max Activating Token Index: 778

Text #6

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2437. Min Act: -0.0000

Data Index: 1260804 (The Pile)

Max Activating Token Index: 1011

Text #7

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2413. Min Act: -0.0000

Data Index: 237422 (The Pile)

Max Activating Token Index: 60

Text #8

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2390. Min Act: -0.0000

Data Index: 1977731 (The Pile)

Max Activating Token Index: 109

Text #9

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2525. Min Act: -0.0000

Data Index: 239492 (The Pile)

Max Activating Token Index: 773

Text #10

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2617. Min Act: -0.0000

Data Index: 574498 (The Pile)

Max Activating Token Index: 38

Text #11

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2510. Min Act: -0.0000

Data Index: 1847286 (The Pile)

Max Activating Token Index: 908

Text #12

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2424. Min Act: -0.0000

Data Index: 838195 (The Pile)

Max Activating Token Index: 137

Text #13

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2407. Min Act: -0.0000

Data Index: 1397740 (The Pile)

Max Activating Token Index: 607

Text #14

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2436. Min Act: -0.0000

Data Index: 1717013 (The Pile)

Max Activating Token Index: 925

Text #15

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2386. Min Act: -0.0000

Data Index: 1434713 (The Pile)

Max Activating Token Index: 124

Text #16

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2372. Min Act: -0.0000

Data Index: 376764 (The Pile)

Max Activating Token Index: 466

Text #17

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2212. Min Act: -0.0000

Data Index: 1786684 (The Pile)

Max Activating Token Index: 666

Text #18

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2264. Min Act: -0.0000

Data Index: 1736521 (The Pile)

Max Activating Token Index: 127

Text #19

Max Range: 0.2973. Min Range: -0.2973

Max Act: 0.2310. Min Act: -0.0000

Data Index: 651003 (The Pile)

Max Activating Token Index: 406