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

Dataset: The Pile

Neuron 2542 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: 0.6931. Min Range: -0.6931

Max Act: 0.6931. Min Act: -0.0000

Data Index: 509959 (The Pile)

Max Activating Token Index: 237

Text #1

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.6420. Min Act: -0.0000

Data Index: 1251987 (The Pile)

Max Activating Token Index: 172

Text #2

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.6459. Min Act: -0.0000

Data Index: 1731492 (The Pile)

Max Activating Token Index: 255

Text #3

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.5643. Min Act: -0.0000

Data Index: 649414 (The Pile)

Max Activating Token Index: 529

Text #4

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.4418. Min Act: -0.0000

Data Index: 1937491 (The Pile)

Max Activating Token Index: 368

Text #5

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.4657. Min Act: -0.0000

Data Index: 1250685 (The Pile)

Max Activating Token Index: 712

Text #6

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.4491. Min Act: -0.0000

Data Index: 167214 (The Pile)

Max Activating Token Index: 774

Text #7

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.4227. Min Act: -0.0000

Data Index: 1521762 (The Pile)

Max Activating Token Index: 384

Text #8

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.4256. Min Act: -0.0000

Data Index: 932665 (The Pile)

Max Activating Token Index: 676

Text #9

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.4394. Min Act: -0.0000

Data Index: 477294 (The Pile)

Max Activating Token Index: 1008

Text #10

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.4115. Min Act: -0.0000

Data Index: 1466437 (The Pile)

Max Activating Token Index: 28

Text #11

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.4448. Min Act: -0.0000

Data Index: 1817401 (The Pile)

Max Activating Token Index: 935

Text #12

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.4391. Min Act: -0.0000

Data Index: 1947645 (The Pile)

Max Activating Token Index: 865

Text #13

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.4136. Min Act: -0.0000

Data Index: 296834 (The Pile)

Max Activating Token Index: 619

Text #14

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.3941. Min Act: -0.0000

Data Index: 1212902 (The Pile)

Max Activating Token Index: 694

Text #15

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.4171. Min Act: -0.0000

Data Index: 848130 (The Pile)

Max Activating Token Index: 430

Text #16

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.3838. Min Act: -0.0000

Data Index: 1218542 (The Pile)

Max Activating Token Index: 124

Text #17

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.3968. Min Act: -0.0000

Data Index: 1849009 (The Pile)

Max Activating Token Index: 200

Text #18

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.3791. Min Act: -0.0000

Data Index: 1263059 (The Pile)

Max Activating Token Index: 255

Text #19

Max Range: 0.6931. Min Range: -0.6931

Max Act: 0.3638. Min Act: -0.0000

Data Index: 866579 (The Pile)

Max Activating Token Index: 861