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

Dataset: The Pile

Neuron 3115 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: 0.6825. Min Range: -0.6825

Max Act: 0.6825. Min Act: -0.0000

Data Index: 428185 (The Pile)

Max Activating Token Index: 703

Text #1

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.6458. Min Act: -0.0000

Data Index: 673540 (The Pile)

Max Activating Token Index: 502

Text #2

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.6189. Min Act: -0.0000

Data Index: 273210 (The Pile)

Max Activating Token Index: 16

Text #3

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.6307. Min Act: -0.0000

Data Index: 1992797 (The Pile)

Max Activating Token Index: 506

Text #4

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.6446. Min Act: -0.0000

Data Index: 11511 (The Pile)

Max Activating Token Index: 141

Text #5

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.6073. Min Act: -0.0000

Data Index: 40055 (The Pile)

Max Activating Token Index: 651

Text #6

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5935. Min Act: -0.0000

Data Index: 1959864 (The Pile)

Max Activating Token Index: 94

Text #7

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5790. Min Act: -0.0000

Data Index: 585684 (The Pile)

Max Activating Token Index: 423

Text #8

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5493. Min Act: -0.0000

Data Index: 447792 (The Pile)

Max Activating Token Index: 190

Text #9

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5774. Min Act: -0.0000

Data Index: 474735 (The Pile)

Max Activating Token Index: 207

Text #10

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5896. Min Act: -0.0000

Data Index: 1816537 (The Pile)

Max Activating Token Index: 426

Text #11

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5606. Min Act: -0.0000

Data Index: 1084152 (The Pile)

Max Activating Token Index: 482

Text #12

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5332. Min Act: -0.0000

Data Index: 1634150 (The Pile)

Max Activating Token Index: 190

Text #13

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5614. Min Act: -0.0000

Data Index: 730774 (The Pile)

Max Activating Token Index: 357

Text #14

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5410. Min Act: -0.0000

Data Index: 1252520 (The Pile)

Max Activating Token Index: 221

Text #15

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5575. Min Act: -0.0000

Data Index: 1763277 (The Pile)

Max Activating Token Index: 525

Text #16

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5193. Min Act: -0.0000

Data Index: 830937 (The Pile)

Max Activating Token Index: 854

Text #17

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5439. Min Act: -0.0000

Data Index: 205768 (The Pile)

Max Activating Token Index: 380

Text #18

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5335. Min Act: -0.0000

Data Index: 1917815 (The Pile)

Max Activating Token Index: 213

Text #19

Max Range: 0.6825. Min Range: -0.6825

Max Act: 0.5262. Min Act: -0.0000

Data Index: 1692550 (The Pile)

Max Activating Token Index: 25