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

Dataset: The Pile

Neuron 1478 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.3576. Min Act: -0.0000

Data Index: 1289474 (The Pile)

Max Activating Token Index: 92

Text #1

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.3581. Min Act: -0.0000

Data Index: 445467 (The Pile)

Max Activating Token Index: 91

Text #2

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.3516. Min Act: -0.0000

Data Index: 1015105 (The Pile)

Max Activating Token Index: 148

Text #3

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.3408. Min Act: -0.0000

Data Index: 1786495 (The Pile)

Max Activating Token Index: 109

Text #4

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.3400. Min Act: -0.0000

Data Index: 1526221 (The Pile)

Max Activating Token Index: 98

Text #5

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.3458. Min Act: -0.0000

Data Index: 897998 (The Pile)

Max Activating Token Index: 96

Text #6

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.3362. Min Act: -0.0000

Data Index: 1411491 (The Pile)

Max Activating Token Index: 106

Text #7

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.3451. Min Act: -0.0000

Data Index: 222174 (The Pile)

Max Activating Token Index: 147

Text #8

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.3304. Min Act: -0.0000

Data Index: 1639365 (The Pile)

Max Activating Token Index: 88

Text #9

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.3656. Min Act: -0.0000

Data Index: 220983 (The Pile)

Max Activating Token Index: 106

Text #10

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.3373. Min Act: -0.0000

Data Index: 1871255 (The Pile)

Max Activating Token Index: 127

Text #11

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.3364. Min Act: -0.0000

Data Index: 1828715 (The Pile)

Max Activating Token Index: 112

Text #12

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.3502. Min Act: -0.0000

Data Index: 706866 (The Pile)

Max Activating Token Index: 121

Text #13

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.3337. Min Act: -0.0000

Data Index: 713666 (The Pile)

Max Activating Token Index: 122

Text #14

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.3242. Min Act: -0.0000

Data Index: 1412960 (The Pile)

Max Activating Token Index: 124

Text #15

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.3037. Min Act: -0.0000

Data Index: 1393468 (The Pile)

Max Activating Token Index: 145

Text #16

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.2989. Min Act: -0.0000

Data Index: 1902364 (The Pile)

Max Activating Token Index: 187

Text #17

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.3297. Min Act: -0.0000

Data Index: 374200 (The Pile)

Max Activating Token Index: 114

Text #18

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.3287. Min Act: -0.0000

Data Index: 1319156 (The Pile)

Max Activating Token Index: 100

Text #19

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.2777. Min Act: -0.0000

Data Index: 1331572 (The Pile)

Max Activating Token Index: 136