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

Dataset: The Pile

Neuron 1814 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.8404. Min Act: -0.0000

Data Index: 1282054 (The Pile)

Max Activating Token Index: 51

Text #1

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.5595. Min Act: -0.0000

Data Index: 1942670 (The Pile)

Max Activating Token Index: 273

Text #2

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.4159. Min Act: -0.0000

Data Index: 1817355 (The Pile)

Max Activating Token Index: 160

Text #3

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.5059. Min Act: -0.0000

Data Index: 1851316 (The Pile)

Max Activating Token Index: 61

Text #4

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.4102. Min Act: -0.0000

Data Index: 1365611 (The Pile)

Max Activating Token Index: 915

Text #5

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.3336. Min Act: -0.0000

Data Index: 938122 (The Pile)

Max Activating Token Index: 600

Text #6

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.3851. Min Act: -0.0000

Data Index: 266625 (The Pile)

Max Activating Token Index: 358

Text #7

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.4238. Min Act: -0.0000

Data Index: 1748148 (The Pile)

Max Activating Token Index: 215

Text #8

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.4066. Min Act: -0.0000

Data Index: 1391228 (The Pile)

Max Activating Token Index: 562

Text #9

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.3900. Min Act: -0.0000

Data Index: 3180 (The Pile)

Max Activating Token Index: 830

Text #10

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.3449. Min Act: -0.0000

Data Index: 438807 (The Pile)

Max Activating Token Index: 430

Text #11

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.3003. Min Act: -0.0000

Data Index: 567880 (The Pile)

Max Activating Token Index: 574

Text #12

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.3864. Min Act: -0.0000

Data Index: 732709 (The Pile)

Max Activating Token Index: 426

Text #13

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.2942. Min Act: -0.0000

Data Index: 351841 (The Pile)

Max Activating Token Index: 220

Text #14

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.2481. Min Act: -0.0000

Data Index: 1968930 (The Pile)

Max Activating Token Index: 51

Text #15

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.2869. Min Act: -0.0000

Data Index: 1587512 (The Pile)

Max Activating Token Index: 330

Text #16

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.2941. Min Act: -0.0000

Data Index: 18817 (The Pile)

Max Activating Token Index: 785

Text #17

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.3223. Min Act: -0.0000

Data Index: 558148 (The Pile)

Max Activating Token Index: 36

Text #18

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.3146. Min Act: -0.0000

Data Index: 1392750 (The Pile)

Max Activating Token Index: 180

Text #19

Max Range: 1.8404. Min Range: -1.8404

Max Act: 1.3076. Min Act: -0.0000

Data Index: 877593 (The Pile)

Max Activating Token Index: 176