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

Dataset: The Pile

Neuron 3943 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.9429. Min Act: -0.0000

Data Index: 1484190 (The Pile)

Max Activating Token Index: 681

Text #1

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.8013. Min Act: -0.0000

Data Index: 335970 (The Pile)

Max Activating Token Index: 952

Text #2

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.7570. Min Act: -0.0000

Data Index: 1207920 (The Pile)

Max Activating Token Index: 830

Text #3

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.7630. Min Act: -0.0000

Data Index: 21782 (The Pile)

Max Activating Token Index: 269

Text #4

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.7456. Min Act: -0.0000

Data Index: 1155246 (The Pile)

Max Activating Token Index: 127

Text #5

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.7490. Min Act: -0.0000

Data Index: 776487 (The Pile)

Max Activating Token Index: 1004

Text #6

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.7697. Min Act: -0.0000

Data Index: 1138826 (The Pile)

Max Activating Token Index: 740

Text #7

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.6646. Min Act: -0.0000

Data Index: 141116 (The Pile)

Max Activating Token Index: 350

Text #8

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.6571. Min Act: -0.0000

Data Index: 1537103 (The Pile)

Max Activating Token Index: 124

Text #9

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.6510. Min Act: -0.0000

Data Index: 463427 (The Pile)

Max Activating Token Index: 772

Text #10

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.6790. Min Act: -0.0000

Data Index: 715809 (The Pile)

Max Activating Token Index: 288

Text #11

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.6540. Min Act: -0.0000

Data Index: 570984 (The Pile)

Max Activating Token Index: 306

Text #12

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.6167. Min Act: -0.0000

Data Index: 1576861 (The Pile)

Max Activating Token Index: 182

Text #13

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.6731. Min Act: -0.0000

Data Index: 674809 (The Pile)

Max Activating Token Index: 650

Text #14

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.6512. Min Act: -0.0000

Data Index: 1775663 (The Pile)

Max Activating Token Index: 109

Text #15

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.6217. Min Act: -0.0000

Data Index: 1673894 (The Pile)

Max Activating Token Index: 443

Text #16

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.6476. Min Act: -0.0000

Data Index: 654748 (The Pile)

Max Activating Token Index: 247

Text #17

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.6444. Min Act: -0.0000

Data Index: 25541 (The Pile)

Max Activating Token Index: 592

Text #18

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.6652. Min Act: -0.0000

Data Index: 1490763 (The Pile)

Max Activating Token Index: 810

Text #19

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.6488. Min Act: -0.0000

Data Index: 1593284 (The Pile)

Max Activating Token Index: 610