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

Dataset: The Pile

Neuron 1003 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.4659. Min Act: -0.0000

Data Index: 1197387 (The Pile)

Max Activating Token Index: 532

Text #1

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.3989. Min Act: -0.0000

Data Index: 1353145 (The Pile)

Max Activating Token Index: 350

Text #2

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.3696. Min Act: -0.0000

Data Index: 639093 (The Pile)

Max Activating Token Index: 184

Text #3

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.3711. Min Act: -0.0000

Data Index: 1563373 (The Pile)

Max Activating Token Index: 245

Text #4

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.3472. Min Act: -0.0000

Data Index: 1650847 (The Pile)

Max Activating Token Index: 264

Text #5

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.3191. Min Act: -0.0000

Data Index: 364009 (The Pile)

Max Activating Token Index: 158

Text #6

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.3835. Min Act: -0.0000

Data Index: 1975380 (The Pile)

Max Activating Token Index: 138

Text #7

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.4026. Min Act: -0.0000

Data Index: 140333 (The Pile)

Max Activating Token Index: 136

Text #8

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.3484. Min Act: -0.0000

Data Index: 634638 (The Pile)

Max Activating Token Index: 551

Text #9

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.2672. Min Act: -0.0000

Data Index: 1813744 (The Pile)

Max Activating Token Index: 384

Text #10

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.3389. Min Act: -0.0000

Data Index: 774831 (The Pile)

Max Activating Token Index: 244

Text #11

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.2503. Min Act: -0.0000

Data Index: 1463168 (The Pile)

Max Activating Token Index: 398

Text #12

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.2849. Min Act: -0.0000

Data Index: 530269 (The Pile)

Max Activating Token Index: 557

Text #13

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.0353. Min Act: -0.0000

Data Index: 1760803 (The Pile)

Max Activating Token Index: 940

Text #14

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.1157. Min Act: -0.0000

Data Index: 666709 (The Pile)

Max Activating Token Index: 792

Text #15

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.2249. Min Act: -0.0000

Data Index: 212134 (The Pile)

Max Activating Token Index: 884

Text #16

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.0652. Min Act: -0.0000

Data Index: 1361809 (The Pile)

Max Activating Token Index: 933

Text #17

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.0121. Min Act: -0.0000

Data Index: 769851 (The Pile)

Max Activating Token Index: 902

Text #18

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.0712. Min Act: -0.0000

Data Index: 1794693 (The Pile)

Max Activating Token Index: 655

Text #19

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.0098. Min Act: -0.0000

Data Index: 846731 (The Pile)

Max Activating Token Index: 532