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

Dataset: The Pile

Neuron 1601 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: 5.5546. Min Range: -5.5546

Max Act: 5.5546. Min Act: -0.0000

Data Index: 1732728 (The Pile)

Max Activating Token Index: 372

Text #1

Max Range: 5.5546. Min Range: -5.5546

Max Act: 5.1504. Min Act: -0.0000

Data Index: 77168 (The Pile)

Max Activating Token Index: 607

Text #2

Max Range: 5.5546. Min Range: -5.5546

Max Act: 4.4475. Min Act: -0.0000

Data Index: 1420186 (The Pile)

Max Activating Token Index: 26

Text #3

Max Range: 5.5546. Min Range: -5.5546

Max Act: 4.6690. Min Act: -0.0000

Data Index: 1616334 (The Pile)

Max Activating Token Index: 777

Text #4

Max Range: 5.5546. Min Range: -5.5546

Max Act: 4.4585. Min Act: -0.0000

Data Index: 969919 (The Pile)

Max Activating Token Index: 177

Text #5

Max Range: 5.5546. Min Range: -5.5546

Max Act: 4.2579. Min Act: -0.0000

Data Index: 80996 (The Pile)

Max Activating Token Index: 614

Text #6

Max Range: 5.5546. Min Range: -5.5546

Max Act: 4.3882. Min Act: -0.0000

Data Index: 1531525 (The Pile)

Max Activating Token Index: 58

Text #7

Max Range: 5.5546. Min Range: -5.5546

Max Act: 4.3187. Min Act: -0.0000

Data Index: 821733 (The Pile)

Max Activating Token Index: 82

Text #8

Max Range: 5.5546. Min Range: -5.5546

Max Act: 4.4838. Min Act: -0.0000

Data Index: 472889 (The Pile)

Max Activating Token Index: 356

Text #9

Max Range: 5.5546. Min Range: -5.5546

Max Act: 4.3424. Min Act: -0.0000

Data Index: 1193082 (The Pile)

Max Activating Token Index: 334

Text #10

Max Range: 5.5546. Min Range: -5.5546

Max Act: 4.1358. Min Act: -0.0000

Data Index: 1604544 (The Pile)

Max Activating Token Index: 362

Text #11

Max Range: 5.5546. Min Range: -5.5546

Max Act: 4.3020. Min Act: -0.0000

Data Index: 1140084 (The Pile)

Max Activating Token Index: 935

Text #12

Max Range: 5.5546. Min Range: -5.5546

Max Act: 4.2062. Min Act: -0.0000

Data Index: 550008 (The Pile)

Max Activating Token Index: 47

Text #13

Max Range: 5.5546. Min Range: -5.5546

Max Act: 3.8412. Min Act: -0.0000

Data Index: 139195 (The Pile)

Max Activating Token Index: 84

Text #14

Max Range: 5.5546. Min Range: -5.5546

Max Act: 3.8596. Min Act: -0.0000

Data Index: 423686 (The Pile)

Max Activating Token Index: 575

Text #15

Max Range: 5.5546. Min Range: -5.5546

Max Act: 3.8580. Min Act: -0.0000

Data Index: 964495 (The Pile)

Max Activating Token Index: 335

Text #16

Max Range: 5.5546. Min Range: -5.5546

Max Act: 3.8352. Min Act: -0.0000

Data Index: 1235483 (The Pile)

Max Activating Token Index: 304

Text #17

Max Range: 5.5546. Min Range: -5.5546

Max Act: 3.9956. Min Act: -0.0000

Data Index: 1808420 (The Pile)

Max Activating Token Index: 34

Text #18

Max Range: 5.5546. Min Range: -5.5546

Max Act: 3.6112. Min Act: -0.0000

Data Index: 1159360 (The Pile)

Max Activating Token Index: 250

Text #19

Max Range: 5.5546. Min Range: -5.5546

Max Act: 3.6804. Min Act: -0.0000

Data Index: 1874946 (The Pile)

Max Activating Token Index: 377