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

Dataset: The Pile

Neuron 634 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: 0.4795. Min Range: -0.4795

Max Act: 0.4795. Min Act: -0.0000

Data Index: 1390653 (The Pile)

Max Activating Token Index: 468

Text #1

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.4340. Min Act: -0.0000

Data Index: 1485779 (The Pile)

Max Activating Token Index: 140

Text #2

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.4605. Min Act: -0.0000

Data Index: 184071 (The Pile)

Max Activating Token Index: 963

Text #3

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.4484. Min Act: -0.0000

Data Index: 1579919 (The Pile)

Max Activating Token Index: 1015

Text #4

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.4408. Min Act: -0.0000

Data Index: 1630115 (The Pile)

Max Activating Token Index: 736

Text #5

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.4329. Min Act: -0.0000

Data Index: 293779 (The Pile)

Max Activating Token Index: 307

Text #6

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.4209. Min Act: 0.0000

Data Index: 1307100 (The Pile)

Max Activating Token Index: 592

Text #7

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.3895. Min Act: -0.0000

Data Index: 56166 (The Pile)

Max Activating Token Index: 156

Text #8

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.3920. Min Act: -0.0000

Data Index: 1031653 (The Pile)

Max Activating Token Index: 479

Text #9

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.3776. Min Act: 0.0000

Data Index: 1429154 (The Pile)

Max Activating Token Index: 744

Text #10

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.4030. Min Act: -0.0000

Data Index: 1965112 (The Pile)

Max Activating Token Index: 938

Text #11

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.3495. Min Act: 0.0000

Data Index: 1177650 (The Pile)

Max Activating Token Index: 106

Text #12

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.3466. Min Act: 0.0000

Data Index: 1859455 (The Pile)

Max Activating Token Index: 877

Text #13

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.3681. Min Act: 0.0000

Data Index: 946889 (The Pile)

Max Activating Token Index: 354

Text #14

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.3686. Min Act: -0.0000

Data Index: 1640355 (The Pile)

Max Activating Token Index: 568

Text #15

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.3772. Min Act: -0.0000

Data Index: 127604 (The Pile)

Max Activating Token Index: 169

Text #16

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.3716. Min Act: -0.0000

Data Index: 1118335 (The Pile)

Max Activating Token Index: 225

Text #17

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.3700. Min Act: -0.0000

Data Index: 1935708 (The Pile)

Max Activating Token Index: 303

Text #18

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.3544. Min Act: -0.0000

Data Index: 896319 (The Pile)

Max Activating Token Index: 26

Text #19

Max Range: 0.4795. Min Range: -0.4795

Max Act: 0.3549. Min Act: -0.0000

Data Index: 1179606 (The Pile)

Max Activating Token Index: 44