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

Dataset: The Pile

Neuron 1800 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1902. Min Range: -3.1902

Max Act: 3.1902. Min Act: -0.0000

Data Index: 1124679 (The Pile)

Max Activating Token Index: 144

Text #1

Max Range: 3.1902. Min Range: -3.1902

Max Act: 2.7438. Min Act: -0.0000

Data Index: 1590255 (The Pile)

Max Activating Token Index: 672

Text #2

Max Range: 3.1902. Min Range: -3.1902

Max Act: 2.4239. Min Act: -0.0000

Data Index: 235656 (The Pile)

Max Activating Token Index: 170

Text #3

Max Range: 3.1902. Min Range: -3.1902

Max Act: 2.3209. Min Act: -0.0000

Data Index: 593780 (The Pile)

Max Activating Token Index: 178

Text #4

Max Range: 3.1902. Min Range: -3.1902

Max Act: 2.4789. Min Act: -0.0000

Data Index: 1730938 (The Pile)

Max Activating Token Index: 131

Text #5

Max Range: 3.1902. Min Range: -3.1902

Max Act: 2.5754. Min Act: -0.0000

Data Index: 237522 (The Pile)

Max Activating Token Index: 215

Text #6

Max Range: 3.1902. Min Range: -3.1902

Max Act: 2.3063. Min Act: -0.0000

Data Index: 1572593 (The Pile)

Max Activating Token Index: 88

Text #7

Max Range: 3.1902. Min Range: -3.1902

Max Act: 2.2869. Min Act: -0.0000

Data Index: 1374310 (The Pile)

Max Activating Token Index: 286

Text #8

Max Range: 3.1902. Min Range: -3.1902

Max Act: 2.1017. Min Act: 0.0001

Data Index: 429899 (The Pile)

Max Activating Token Index: 623

Text #9

Max Range: 3.1902. Min Range: -3.1902

Max Act: 1.9577. Min Act: -0.0000

Data Index: 1654372 (The Pile)

Max Activating Token Index: 282

Text #10

Max Range: 3.1902. Min Range: -3.1902

Max Act: 2.2996. Min Act: -0.0000

Data Index: 1394378 (The Pile)

Max Activating Token Index: 288

Text #11

Max Range: 3.1902. Min Range: -3.1902

Max Act: 2.1359. Min Act: -0.0000

Data Index: 461377 (The Pile)

Max Activating Token Index: 722

Text #12

Max Range: 3.1902. Min Range: -3.1902

Max Act: 1.9341. Min Act: -0.0000

Data Index: 1000171 (The Pile)

Max Activating Token Index: 941

Text #13

Max Range: 3.1902. Min Range: -3.1902

Max Act: 2.1161. Min Act: 0.0000

Data Index: 860385 (The Pile)

Max Activating Token Index: 467

Text #14

Max Range: 3.1902. Min Range: -3.1902

Max Act: 2.0283. Min Act: 0.0001

Data Index: 525004 (The Pile)

Max Activating Token Index: 447

Text #15

Max Range: 3.1902. Min Range: -3.1902

Max Act: 2.1341. Min Act: 0.0002

Data Index: 1691679 (The Pile)

Max Activating Token Index: 850

Text #16

Max Range: 3.1902. Min Range: -3.1902

Max Act: 1.9589. Min Act: -0.0000

Data Index: 1248067 (The Pile)

Max Activating Token Index: 527

Text #17

Max Range: 3.1902. Min Range: -3.1902

Max Act: 1.9314. Min Act: -0.0000

Data Index: 1808837 (The Pile)

Max Activating Token Index: 859

Text #18

Max Range: 3.1902. Min Range: -3.1902

Max Act: 1.9261. Min Act: 0.0001

Data Index: 1012606 (The Pile)

Max Activating Token Index: 678

Text #19

Max Range: 3.1902. Min Range: -3.1902

Max Act: 1.7201. Min Act: -0.0000

Data Index: 1616743 (The Pile)

Max Activating Token Index: 554