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

Dataset: The Pile

Neuron 572 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.5901. Min Range: -3.5901

Max Act: 3.5901. Min Act: -0.0000

Data Index: 891997 (The Pile)

Max Activating Token Index: 265

Text #1

Max Range: 3.5901. Min Range: -3.5901

Max Act: 3.5510. Min Act: -0.0000

Data Index: 402525 (The Pile)

Max Activating Token Index: 480

Text #2

Max Range: 3.5901. Min Range: -3.5901

Max Act: 3.4551. Min Act: -0.0000

Data Index: 1237203 (The Pile)

Max Activating Token Index: 238

Text #3

Max Range: 3.5901. Min Range: -3.5901

Max Act: 3.0972. Min Act: -0.0000

Data Index: 587960 (The Pile)

Max Activating Token Index: 194

Text #4

Max Range: 3.5901. Min Range: -3.5901

Max Act: 3.0588. Min Act: -0.0000

Data Index: 1823238 (The Pile)

Max Activating Token Index: 371

Text #5

Max Range: 3.5901. Min Range: -3.5901

Max Act: 3.0062. Min Act: -0.0000

Data Index: 342882 (The Pile)

Max Activating Token Index: 557

Text #6

Max Range: 3.5901. Min Range: -3.5901

Max Act: 3.1253. Min Act: -0.0000

Data Index: 1024915 (The Pile)

Max Activating Token Index: 514

Text #7

Max Range: 3.5901. Min Range: -3.5901

Max Act: 3.0965. Min Act: -0.0000

Data Index: 291346 (The Pile)

Max Activating Token Index: 506

Text #8

Max Range: 3.5901. Min Range: -3.5901

Max Act: 3.0800. Min Act: -0.0000

Data Index: 245918 (The Pile)

Max Activating Token Index: 290

Text #9

Max Range: 3.5901. Min Range: -3.5901

Max Act: 2.9121. Min Act: -0.0000

Data Index: 1450645 (The Pile)

Max Activating Token Index: 330

Text #10

Max Range: 3.5901. Min Range: -3.5901

Max Act: 3.0441. Min Act: -0.0000

Data Index: 220481 (The Pile)

Max Activating Token Index: 70

Text #11

Max Range: 3.5901. Min Range: -3.5901

Max Act: 3.0560. Min Act: -0.0000

Data Index: 1469162 (The Pile)

Max Activating Token Index: 433

Text #12

Max Range: 3.5901. Min Range: -3.5901

Max Act: 3.1577. Min Act: -0.0000

Data Index: 314301 (The Pile)

Max Activating Token Index: 505

Text #13

Max Range: 3.5901. Min Range: -3.5901

Max Act: 2.8518. Min Act: -0.0000

Data Index: 1704202 (The Pile)

Max Activating Token Index: 1007

Text #14

Max Range: 3.5901. Min Range: -3.5901

Max Act: 2.8358. Min Act: -0.0000

Data Index: 1733245 (The Pile)

Max Activating Token Index: 207

Text #15

Max Range: 3.5901. Min Range: -3.5901

Max Act: 2.8437. Min Act: -0.0000

Data Index: 1854418 (The Pile)

Max Activating Token Index: 719

Text #16

Max Range: 3.5901. Min Range: -3.5901

Max Act: 2.6726. Min Act: -0.0000

Data Index: 767099 (The Pile)

Max Activating Token Index: 730

Text #17

Max Range: 3.5901. Min Range: -3.5901

Max Act: 2.7913. Min Act: -0.0000

Data Index: 1836857 (The Pile)

Max Activating Token Index: 97

Text #18

Max Range: 3.5901. Min Range: -3.5901

Max Act: 2.9209. Min Act: -0.0000

Data Index: 324156 (The Pile)

Max Activating Token Index: 602

Text #19

Max Range: 3.5901. Min Range: -3.5901

Max Act: 3.0450. Min Act: -0.0000

Data Index: 1186068 (The Pile)

Max Activating Token Index: 355