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

Dataset: The Pile

Neuron 2435 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: 0.5490. Min Range: -0.5490

Max Act: 0.5490. Min Act: 0.0000

Data Index: 970306 (The Pile)

Max Activating Token Index: 188

Text #1

Max Range: 0.5490. Min Range: -0.5490

Max Act: 0.5152. Min Act: -0.0000

Data Index: 1427894 (The Pile)

Max Activating Token Index: 609

Text #2

Max Range: 0.5490. Min Range: -0.5490

Max Act: 0.5056. Min Act: 0.0000

Data Index: 1381595 (The Pile)

Max Activating Token Index: 626

Text #3

Max Range: 0.5490. Min Range: -0.5490

Max Act: 0.4888. Min Act: -0.0000

Data Index: 1792042 (The Pile)

Max Activating Token Index: 944

Text #4

Max Range: 0.5490. Min Range: -0.5490

Max Act: 0.4339. Min Act: -0.0000

Data Index: 1261384 (The Pile)

Max Activating Token Index: 672

Text #5

Max Range: 0.5490. Min Range: -0.5490

Max Act: 0.4414. Min Act: 0.0000

Data Index: 1304271 (The Pile)

Max Activating Token Index: 404

Text #6

Max Range: 0.5490. Min Range: -0.5490

Max Act: 0.4165. Min Act: 0.0000

Data Index: 794983 (The Pile)

Max Activating Token Index: 448

Text #7

Max Range: 0.5490. Min Range: -0.5490

Max Act: 0.4237. Min Act: -0.0000

Data Index: 883562 (The Pile)

Max Activating Token Index: 945

Text #8

Max Range: 0.5490. Min Range: -0.5490

Max Act: 0.3661. Min Act: -0.0000

Data Index: 740062 (The Pile)

Max Activating Token Index: 620

Text #9

Max Range: 0.5490. Min Range: -0.5490

Max Act: 0.4023. Min Act: -0.0000

Data Index: 1267122 (The Pile)

Max Activating Token Index: 990

Text #10

Max Range: 0.5490. Min Range: -0.5490

Max Act: 0.3899. Min Act: -0.0000

Data Index: 1861732 (The Pile)

Max Activating Token Index: 252

Text #11

Max Range: 0.5490. Min Range: -0.5490

Max Act: 0.3820. Min Act: 0.0000

Data Index: 112244 (The Pile)

Max Activating Token Index: 291

Text #12

Max Range: 0.5490. Min Range: -0.5490

Max Act: 0.3763. Min Act: -0.0000

Data Index: 1056238 (The Pile)

Max Activating Token Index: 655

Text #13

Max Range: 0.5490. Min Range: -0.5490

Max Act: 0.3808. Min Act: -0.0000

Data Index: 886635 (The Pile)

Max Activating Token Index: 923

Text #14

Max Range: 0.5490. Min Range: -0.5490

Max Act: 0.3791. Min Act: 0.0000

Data Index: 1335400 (The Pile)

Max Activating Token Index: 615

Text #15

Max Range: 0.5490. Min Range: -0.5490

Max Act: 0.3778. Min Act: -0.0000

Data Index: 1115312 (The Pile)

Max Activating Token Index: 38

Text #16

Max Range: 0.5490. Min Range: -0.5490

Max Act: 0.3759. Min Act: 0.0000

Data Index: 586741 (The Pile)

Max Activating Token Index: 295

Text #17

Max Range: 0.5490. Min Range: -0.5490

Max Act: 0.3763. Min Act: 0.0000

Data Index: 558105 (The Pile)

Max Activating Token Index: 597

Text #18

Max Range: 0.5490. Min Range: -0.5490

Max Act: 0.3749. Min Act: -0.0000

Data Index: 1018927 (The Pile)

Max Activating Token Index: 503

Text #19

Max Range: 0.5490. Min Range: -0.5490

Max Act: 0.3691. Min Act: -0.0000

Data Index: 1750601 (The Pile)

Max Activating Token Index: 217