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

Dataset: The Pile

Neuron 4257 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5717. Min Range: -1.5717

Max Act: 1.5717. Min Act: -0.0000

Data Index: 507540 (The Pile)

Max Activating Token Index: 602

Text #1

Max Range: 1.5717. Min Range: -1.5717

Max Act: 1.5232. Min Act: -0.0000

Data Index: 1322091 (The Pile)

Max Activating Token Index: 783

Text #2

Max Range: 1.5717. Min Range: -1.5717

Max Act: 1.4778. Min Act: -0.0000

Data Index: 111475 (The Pile)

Max Activating Token Index: 480

Text #3

Max Range: 1.5717. Min Range: -1.5717

Max Act: 1.4639. Min Act: -0.0000

Data Index: 1308081 (The Pile)

Max Activating Token Index: 524

Text #4

Max Range: 1.5717. Min Range: -1.5717

Max Act: 1.4548. Min Act: -0.0000

Data Index: 358289 (The Pile)

Max Activating Token Index: 612

Text #5

Max Range: 1.5717. Min Range: -1.5717

Max Act: 1.4216. Min Act: -0.0000

Data Index: 1824849 (The Pile)

Max Activating Token Index: 61

Text #6

Max Range: 1.5717. Min Range: -1.5717

Max Act: 1.4129. Min Act: -0.0000

Data Index: 228405 (The Pile)

Max Activating Token Index: 703

Text #7

Max Range: 1.5717. Min Range: -1.5717

Max Act: 1.3892. Min Act: -0.0000

Data Index: 553785 (The Pile)

Max Activating Token Index: 684

Text #8

Max Range: 1.5717. Min Range: -1.5717

Max Act: 1.3905. Min Act: -0.0000

Data Index: 385705 (The Pile)

Max Activating Token Index: 520

Text #9

Max Range: 1.5717. Min Range: -1.5717

Max Act: 1.3761. Min Act: -0.0000

Data Index: 1063720 (The Pile)

Max Activating Token Index: 613

Text #10

Max Range: 1.5717. Min Range: -1.5717

Max Act: 1.2921. Min Act: -0.0000

Data Index: 1799809 (The Pile)

Max Activating Token Index: 128

Text #11

Max Range: 1.5717. Min Range: -1.5717

Max Act: 1.3460. Min Act: -0.0000

Data Index: 666385 (The Pile)

Max Activating Token Index: 849

Text #12

Max Range: 1.5717. Min Range: -1.5717

Max Act: 1.3702. Min Act: -0.0000

Data Index: 972631 (The Pile)

Max Activating Token Index: 21

Text #13

Max Range: 1.5717. Min Range: -1.5717

Max Act: 1.3293. Min Act: -0.0000

Data Index: 132923 (The Pile)

Max Activating Token Index: 685

Text #14

Max Range: 1.5717. Min Range: -1.5717

Max Act: 1.4019. Min Act: -0.0000

Data Index: 1537466 (The Pile)

Max Activating Token Index: 589

Text #15

Max Range: 1.5717. Min Range: -1.5717

Max Act: 1.3204. Min Act: -0.0000

Data Index: 1076202 (The Pile)

Max Activating Token Index: 12

Text #16

Max Range: 1.5717. Min Range: -1.5717

Max Act: 1.2267. Min Act: -0.0000

Data Index: 1854391 (The Pile)

Max Activating Token Index: 738

Text #17

Max Range: 1.5717. Min Range: -1.5717

Max Act: 1.2348. Min Act: -0.0000

Data Index: 1612162 (The Pile)

Max Activating Token Index: 473

Text #18

Max Range: 1.5717. Min Range: -1.5717

Max Act: 1.3045. Min Act: -0.0000

Data Index: 831584 (The Pile)

Max Activating Token Index: 327

Text #19

Max Range: 1.5717. Min Range: -1.5717

Max Act: 1.2166. Min Act: -0.0000

Data Index: 573178 (The Pile)

Max Activating Token Index: 60