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

Dataset: The Pile

Neuron 1066 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.3670. Min Act: -0.0000

Data Index: 1749116 (The Pile)

Max Activating Token Index: 744

Text #1

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.3117. Min Act: -0.0000

Data Index: 1663364 (The Pile)

Max Activating Token Index: 460

Text #2

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.3350. Min Act: -0.0000

Data Index: 1429155 (The Pile)

Max Activating Token Index: 157

Text #3

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.3292. Min Act: -0.0000

Data Index: 1456208 (The Pile)

Max Activating Token Index: 265

Text #4

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2974. Min Act: -0.0000

Data Index: 1028401 (The Pile)

Max Activating Token Index: 771

Text #5

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.3022. Min Act: -0.0000

Data Index: 1876128 (The Pile)

Max Activating Token Index: 298

Text #6

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2715. Min Act: -0.0000

Data Index: 1390848 (The Pile)

Max Activating Token Index: 143

Text #7

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.3107. Min Act: -0.0000

Data Index: 1388983 (The Pile)

Max Activating Token Index: 620

Text #8

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2980. Min Act: -0.0000

Data Index: 397735 (The Pile)

Max Activating Token Index: 169

Text #9

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2753. Min Act: -0.0000

Data Index: 162511 (The Pile)

Max Activating Token Index: 295

Text #10

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2868. Min Act: -0.0000

Data Index: 1860264 (The Pile)

Max Activating Token Index: 574

Text #11

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2683. Min Act: -0.0000

Data Index: 391902 (The Pile)

Max Activating Token Index: 517

Text #12

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2739. Min Act: -0.0000

Data Index: 1481226 (The Pile)

Max Activating Token Index: 786

Text #13

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2374. Min Act: -0.0000

Data Index: 160149 (The Pile)

Max Activating Token Index: 955

Text #14

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2586. Min Act: -0.0000

Data Index: 1709864 (The Pile)

Max Activating Token Index: 464

Text #15

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2488. Min Act: -0.0000

Data Index: 38165 (The Pile)

Max Activating Token Index: 287

Text #16

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2271. Min Act: -0.0000

Data Index: 110658 (The Pile)

Max Activating Token Index: 815

Text #17

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2202. Min Act: -0.0000

Data Index: 476413 (The Pile)

Max Activating Token Index: 564

Text #18

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2526. Min Act: -0.0000

Data Index: 1555962 (The Pile)

Max Activating Token Index: 333

Text #19

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2613. Min Act: -0.0000

Data Index: 320825 (The Pile)

Max Activating Token Index: 939