Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 331 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0829. Min Range: -1.0829

Max Act: 1.0829. Min Act: -0.0000

Data Index: 1853354 (The Pile)

Max Activating Token Index: 58

Text #1

Max Range: 1.0829. Min Range: -1.0829

Max Act: 1.0230. Min Act: -0.0000

Data Index: 1791360 (The Pile)

Max Activating Token Index: 371

Text #2

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.9649. Min Act: -0.0000

Data Index: 1431205 (The Pile)

Max Activating Token Index: 882

Text #3

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.8735. Min Act: -0.0000

Data Index: 1275905 (The Pile)

Max Activating Token Index: 846

Text #4

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.9293. Min Act: -0.0000

Data Index: 1762310 (The Pile)

Max Activating Token Index: 107

Text #5

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.9524. Min Act: -0.0000

Data Index: 636985 (The Pile)

Max Activating Token Index: 258

Text #6

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.9834. Min Act: -0.0000

Data Index: 821916 (The Pile)

Max Activating Token Index: 825

Text #7

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.9361. Min Act: -0.0000

Data Index: 503047 (The Pile)

Max Activating Token Index: 798

Text #8

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.8991. Min Act: -0.0000

Data Index: 1499975 (The Pile)

Max Activating Token Index: 423

Text #9

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.8840. Min Act: -0.0000

Data Index: 498921 (The Pile)

Max Activating Token Index: 250

Text #10

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.9045. Min Act: -0.0000

Data Index: 1879768 (The Pile)

Max Activating Token Index: 618

Text #11

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.8595. Min Act: -0.0000

Data Index: 256841 (The Pile)

Max Activating Token Index: 748

Text #12

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.8448. Min Act: -0.0000

Data Index: 1839345 (The Pile)

Max Activating Token Index: 250

Text #13

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.9217. Min Act: -0.0000

Data Index: 1575230 (The Pile)

Max Activating Token Index: 63

Text #14

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.8409. Min Act: -0.0000

Data Index: 34141 (The Pile)

Max Activating Token Index: 430

Text #15

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.8349. Min Act: -0.0000

Data Index: 959311 (The Pile)

Max Activating Token Index: 135

Text #16

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.9034. Min Act: -0.0000

Data Index: 1421130 (The Pile)

Max Activating Token Index: 413

Text #17

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.8791. Min Act: -0.0000

Data Index: 1086053 (The Pile)

Max Activating Token Index: 448

Text #18

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.8665. Min Act: -0.0000

Data Index: 676005 (The Pile)

Max Activating Token Index: 635

Text #19

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.8028. Min Act: -0.0000

Data Index: 1530587 (The Pile)

Max Activating Token Index: 57