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

Dataset: The Pile

Neuron 2859 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: 0.8271. Min Range: -0.8271

Max Act: 0.8271. Min Act: -0.0000

Data Index: 1515251 (The Pile)

Max Activating Token Index: 703

Text #1

Max Range: 0.8271. Min Range: -0.8271

Max Act: 0.7051. Min Act: -0.0000

Data Index: 1049962 (The Pile)

Max Activating Token Index: 249

Text #2

Max Range: 0.8271. Min Range: -0.8271

Max Act: 0.6278. Min Act: -0.0000

Data Index: 1465883 (The Pile)

Max Activating Token Index: 691

Text #3

Max Range: 0.8271. Min Range: -0.8271

Max Act: 0.6288. Min Act: -0.0000

Data Index: 556760 (The Pile)

Max Activating Token Index: 717

Text #4

Max Range: 0.8271. Min Range: -0.8271

Max Act: 0.6097. Min Act: -0.0000

Data Index: 971614 (The Pile)

Max Activating Token Index: 1014

Text #5

Max Range: 0.8271. Min Range: -0.8271

Max Act: 0.6796. Min Act: -0.0000

Data Index: 1191684 (The Pile)

Max Activating Token Index: 952

Text #6

Max Range: 0.8271. Min Range: -0.8271

Max Act: 0.5962. Min Act: -0.0000

Data Index: 348587 (The Pile)

Max Activating Token Index: 278

Text #7

Max Range: 0.8271. Min Range: -0.8271

Max Act: 0.5851. Min Act: -0.0000

Data Index: 729802 (The Pile)

Max Activating Token Index: 561

Text #8

Max Range: 0.8271. Min Range: -0.8271

Max Act: 0.5491. Min Act: -0.0000

Data Index: 1457705 (The Pile)

Max Activating Token Index: 323

Text #9

Max Range: 0.8271. Min Range: -0.8271

Max Act: 0.5922. Min Act: -0.0000

Data Index: 1633208 (The Pile)

Max Activating Token Index: 629

Text #10

Max Range: 0.8271. Min Range: -0.8271

Max Act: 0.5011. Min Act: -0.0000

Data Index: 127753 (The Pile)

Max Activating Token Index: 647

Text #11

Max Range: 0.8271. Min Range: -0.8271

Max Act: 0.5629. Min Act: -0.0000

Data Index: 593393 (The Pile)

Max Activating Token Index: 760

Text #12

Max Range: 0.8271. Min Range: -0.8271

Max Act: 0.5071. Min Act: -0.0000

Data Index: 751437 (The Pile)

Max Activating Token Index: 364

Text #13

Max Range: 0.8271. Min Range: -0.8271

Max Act: 0.4923. Min Act: -0.0000

Data Index: 1687102 (The Pile)

Max Activating Token Index: 985

Text #14

Max Range: 0.8271. Min Range: -0.8271

Max Act: 0.5480. Min Act: -0.0000

Data Index: 1508724 (The Pile)

Max Activating Token Index: 177

Text #15

Max Range: 0.8271. Min Range: -0.8271

Max Act: 0.5216. Min Act: -0.0000

Data Index: 782634 (The Pile)

Max Activating Token Index: 167

Text #16

Max Range: 0.8271. Min Range: -0.8271

Max Act: 0.4612. Min Act: -0.0000

Data Index: 172784 (The Pile)

Max Activating Token Index: 922

Text #17

Max Range: 0.8271. Min Range: -0.8271

Max Act: 0.4532. Min Act: -0.0000

Data Index: 935472 (The Pile)

Max Activating Token Index: 139

Text #18

Max Range: 0.8271. Min Range: -0.8271

Max Act: 0.5514. Min Act: -0.0000

Data Index: 1889929 (The Pile)

Max Activating Token Index: 472

Text #19

Max Range: 0.8271. Min Range: -0.8271

Max Act: 0.5139. Min Act: -0.0000

Data Index: 141828 (The Pile)

Max Activating Token Index: 904