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

Dataset: The Pile

Neuron 4788 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: 3.4104. Min Range: -3.4104

Max Act: 3.4104. Min Act: -0.0000

Data Index: 1251173 (The Pile)

Max Activating Token Index: 228

Text #1

Max Range: 3.4104. Min Range: -3.4104

Max Act: 3.1322. Min Act: -0.0000

Data Index: 368374 (The Pile)

Max Activating Token Index: 368

Text #2

Max Range: 3.4104. Min Range: -3.4104

Max Act: 3.1268. Min Act: -0.0000

Data Index: 1561348 (The Pile)

Max Activating Token Index: 65

Text #3

Max Range: 3.4104. Min Range: -3.4104

Max Act: 3.0939. Min Act: -0.0000

Data Index: 749609 (The Pile)

Max Activating Token Index: 235

Text #4

Max Range: 3.4104. Min Range: -3.4104

Max Act: 3.1439. Min Act: -0.0000

Data Index: 1837379 (The Pile)

Max Activating Token Index: 563

Text #5

Max Range: 3.4104. Min Range: -3.4104

Max Act: 2.9864. Min Act: -0.0000

Data Index: 1024802 (The Pile)

Max Activating Token Index: 580

Text #6

Max Range: 3.4104. Min Range: -3.4104

Max Act: 2.9889. Min Act: -0.0000

Data Index: 782711 (The Pile)

Max Activating Token Index: 490

Text #7

Max Range: 3.4104. Min Range: -3.4104

Max Act: 2.9740. Min Act: -0.0000

Data Index: 1233275 (The Pile)

Max Activating Token Index: 753

Text #8

Max Range: 3.4104. Min Range: -3.4104

Max Act: 2.9407. Min Act: -0.0000

Data Index: 959445 (The Pile)

Max Activating Token Index: 737

Text #9

Max Range: 3.4104. Min Range: -3.4104

Max Act: 2.9444. Min Act: -0.0000

Data Index: 741600 (The Pile)

Max Activating Token Index: 634

Text #10

Max Range: 3.4104. Min Range: -3.4104

Max Act: 2.9345. Min Act: -0.0000

Data Index: 1747067 (The Pile)

Max Activating Token Index: 970

Text #11

Max Range: 3.4104. Min Range: -3.4104

Max Act: 2.8009. Min Act: -0.0000

Data Index: 1095368 (The Pile)

Max Activating Token Index: 826

Text #12

Max Range: 3.4104. Min Range: -3.4104

Max Act: 2.8963. Min Act: -0.0000

Data Index: 1090241 (The Pile)

Max Activating Token Index: 254

Text #13

Max Range: 3.4104. Min Range: -3.4104

Max Act: 2.7207. Min Act: -0.0000

Data Index: 14612 (The Pile)

Max Activating Token Index: 483

Text #14

Max Range: 3.4104. Min Range: -3.4104

Max Act: 2.7303. Min Act: -0.0000

Data Index: 1452848 (The Pile)

Max Activating Token Index: 189

Text #15

Max Range: 3.4104. Min Range: -3.4104

Max Act: 2.8492. Min Act: -0.0000

Data Index: 1090577 (The Pile)

Max Activating Token Index: 531

Text #16

Max Range: 3.4104. Min Range: -3.4104

Max Act: 2.8314. Min Act: -0.0000

Data Index: 1473526 (The Pile)

Max Activating Token Index: 528

Text #17

Max Range: 3.4104. Min Range: -3.4104

Max Act: 2.8276. Min Act: -0.0000

Data Index: 647872 (The Pile)

Max Activating Token Index: 963

Text #18

Max Range: 3.4104. Min Range: -3.4104

Max Act: 2.6880. Min Act: -0.0000

Data Index: 647418 (The Pile)

Max Activating Token Index: 827

Text #19

Max Range: 3.4104. Min Range: -3.4104

Max Act: 2.6673. Min Act: -0.0000

Data Index: 1493739 (The Pile)

Max Activating Token Index: 605