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

Dataset: The Pile

Neuron 4619 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: 0.8760. Min Range: -0.8760

Max Act: 0.8760. Min Act: -0.0000

Data Index: 945685 (The Pile)

Max Activating Token Index: 769

Text #1

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.6654. Min Act: -0.0000

Data Index: 1432574 (The Pile)

Max Activating Token Index: 313

Text #2

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.6189. Min Act: -0.0000

Data Index: 964348 (The Pile)

Max Activating Token Index: 142

Text #3

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.6015. Min Act: -0.0000

Data Index: 851646 (The Pile)

Max Activating Token Index: 715

Text #4

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.6295. Min Act: -0.0000

Data Index: 255778 (The Pile)

Max Activating Token Index: 707

Text #5

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.6222. Min Act: -0.0000

Data Index: 1183181 (The Pile)

Max Activating Token Index: 456

Text #6

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.6129. Min Act: -0.0000

Data Index: 20479 (The Pile)

Max Activating Token Index: 765

Text #7

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.5856. Min Act: -0.0000

Data Index: 118007 (The Pile)

Max Activating Token Index: 436

Text #8

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.5202. Min Act: -0.0000

Data Index: 701450 (The Pile)

Max Activating Token Index: 203

Text #9

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.5754. Min Act: -0.0000

Data Index: 1225505 (The Pile)

Max Activating Token Index: 933

Text #10

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.5425. Min Act: -0.0000

Data Index: 561185 (The Pile)

Max Activating Token Index: 620

Text #11

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.4542. Min Act: -0.0000

Data Index: 539378 (The Pile)

Max Activating Token Index: 831

Text #12

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.5003. Min Act: -0.0000

Data Index: 796358 (The Pile)

Max Activating Token Index: 315

Text #13

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.5076. Min Act: -0.0000

Data Index: 1769081 (The Pile)

Max Activating Token Index: 225

Text #14

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.5172. Min Act: -0.0000

Data Index: 716653 (The Pile)

Max Activating Token Index: 537

Text #15

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.4988. Min Act: -0.0000

Data Index: 536489 (The Pile)

Max Activating Token Index: 55

Text #16

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.5163. Min Act: -0.0000

Data Index: 147148 (The Pile)

Max Activating Token Index: 13

Text #17

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.5077. Min Act: -0.0000

Data Index: 1288984 (The Pile)

Max Activating Token Index: 537

Text #18

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.5070. Min Act: -0.0000

Data Index: 680827 (The Pile)

Max Activating Token Index: 123

Text #19

Max Range: 0.8760. Min Range: -0.8760

Max Act: 0.4890. Min Act: -0.0000

Data Index: 411447 (The Pile)

Max Activating Token Index: 543