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

Dataset: The Pile

Neuron 3294 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6815. Min Range: -5.6815

Max Act: 5.3804. Min Act: -0.0000

Data Index: 128726 (The Pile)

Max Activating Token Index: 756

Text #1

Max Range: 5.6815. Min Range: -5.6815

Max Act: 5.6815. Min Act: -0.0000

Data Index: 1430641 (The Pile)

Max Activating Token Index: 886

Text #2

Max Range: 5.6815. Min Range: -5.6815

Max Act: 4.7367. Min Act: -0.0000

Data Index: 316242 (The Pile)

Max Activating Token Index: 684

Text #3

Max Range: 5.6815. Min Range: -5.6815

Max Act: 4.4747. Min Act: -0.0000

Data Index: 354798 (The Pile)

Max Activating Token Index: 573

Text #4

Max Range: 5.6815. Min Range: -5.6815

Max Act: 3.6075. Min Act: -0.0000

Data Index: 1575753 (The Pile)

Max Activating Token Index: 580

Text #5

Max Range: 5.6815. Min Range: -5.6815

Max Act: 3.6418. Min Act: -0.0000

Data Index: 1921625 (The Pile)

Max Activating Token Index: 320

Text #6

Max Range: 5.6815. Min Range: -5.6815

Max Act: 3.4855. Min Act: -0.0000

Data Index: 515225 (The Pile)

Max Activating Token Index: 387

Text #7

Max Range: 5.6815. Min Range: -5.6815

Max Act: 3.1652. Min Act: -0.0000

Data Index: 620149 (The Pile)

Max Activating Token Index: 346

Text #8

Max Range: 5.6815. Min Range: -5.6815

Max Act: 3.2910. Min Act: -0.0000

Data Index: 622435 (The Pile)

Max Activating Token Index: 358

Text #9

Max Range: 5.6815. Min Range: -5.6815

Max Act: 3.2295. Min Act: -0.0000

Data Index: 1493870 (The Pile)

Max Activating Token Index: 302

Text #10

Max Range: 5.6815. Min Range: -5.6815

Max Act: 3.0393. Min Act: -0.0000

Data Index: 936509 (The Pile)

Max Activating Token Index: 230

Text #11

Max Range: 5.6815. Min Range: -5.6815

Max Act: 3.3428. Min Act: -0.0000

Data Index: 245040 (The Pile)

Max Activating Token Index: 391

Text #12

Max Range: 5.6815. Min Range: -5.6815

Max Act: 2.9963. Min Act: -0.0000

Data Index: 782119 (The Pile)

Max Activating Token Index: 307

Text #13

Max Range: 5.6815. Min Range: -5.6815

Max Act: 2.9863. Min Act: -0.0000

Data Index: 187487 (The Pile)

Max Activating Token Index: 806

Text #14

Max Range: 5.6815. Min Range: -5.6815

Max Act: 3.2993. Min Act: -0.0000

Data Index: 1769155 (The Pile)

Max Activating Token Index: 347

Text #15

Max Range: 5.6815. Min Range: -5.6815

Max Act: 3.0178. Min Act: -0.0000

Data Index: 1703125 (The Pile)

Max Activating Token Index: 439

Text #16

Max Range: 5.6815. Min Range: -5.6815

Max Act: 2.7151. Min Act: -0.0000

Data Index: 1791417 (The Pile)

Max Activating Token Index: 828

Text #17

Max Range: 5.6815. Min Range: -5.6815

Max Act: 2.9023. Min Act: -0.0000

Data Index: 1484674 (The Pile)

Max Activating Token Index: 965

Text #18

Max Range: 5.6815. Min Range: -5.6815

Max Act: 2.7299. Min Act: -0.0000

Data Index: 643972 (The Pile)

Max Activating Token Index: 245

Text #19

Max Range: 5.6815. Min Range: -5.6815

Max Act: 2.8086. Min Act: -0.0000

Data Index: 1498966 (The Pile)

Max Activating Token Index: 360