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

Dataset: The Pile

Neuron 3287 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: 1.1727. Min Range: -1.1727

Max Act: 1.1727. Min Act: -0.0000

Data Index: 629823 (The Pile)

Max Activating Token Index: 43

Text #1

Max Range: 1.1727. Min Range: -1.1727

Max Act: 1.1008. Min Act: -0.0000

Data Index: 642195 (The Pile)

Max Activating Token Index: 35

Text #2

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.9773. Min Act: -0.0000

Data Index: 656771 (The Pile)

Max Activating Token Index: 48

Text #3

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.9306. Min Act: -0.0000

Data Index: 1151011 (The Pile)

Max Activating Token Index: 61

Text #4

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.5430. Min Act: -0.0000

Data Index: 1689683 (The Pile)

Max Activating Token Index: 980

Text #5

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.4746. Min Act: -0.0000

Data Index: 1701961 (The Pile)

Max Activating Token Index: 179

Text #6

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.4746. Min Act: -0.0000

Data Index: 1474599 (The Pile)

Max Activating Token Index: 179

Text #7

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.4568. Min Act: -0.0000

Data Index: 52824 (The Pile)

Max Activating Token Index: 1015

Text #8

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.4712. Min Act: -0.0000

Data Index: 1936841 (The Pile)

Max Activating Token Index: 422

Text #9

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.3865. Min Act: -0.0000

Data Index: 1951951 (The Pile)

Max Activating Token Index: 221

Text #10

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.4362. Min Act: -0.0000

Data Index: 102969 (The Pile)

Max Activating Token Index: 978

Text #11

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.5267. Min Act: -0.0000

Data Index: 1847323 (The Pile)

Max Activating Token Index: 155

Text #12

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.4376. Min Act: -0.0000

Data Index: 1457455 (The Pile)

Max Activating Token Index: 375

Text #13

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.4576. Min Act: -0.0000

Data Index: 1644486 (The Pile)

Max Activating Token Index: 181

Text #14

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.4250. Min Act: -0.0000

Data Index: 1659380 (The Pile)

Max Activating Token Index: 774

Text #15

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.4380. Min Act: -0.0000

Data Index: 174394 (The Pile)

Max Activating Token Index: 237

Text #16

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.4548. Min Act: -0.0000

Data Index: 283515 (The Pile)

Max Activating Token Index: 506

Text #17

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.4098. Min Act: -0.0000

Data Index: 1454921 (The Pile)

Max Activating Token Index: 780

Text #18

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.4119. Min Act: -0.0000

Data Index: 1860342 (The Pile)

Max Activating Token Index: 373

Text #19

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.4138. Min Act: -0.0000

Data Index: 761516 (The Pile)

Max Activating Token Index: 290