Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 306 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 5.0842. Min Range: -5.0842

Max Act: 5.0842. Min Act: -0.0000

Data Index: 1513630 (The Pile)

Max Activating Token Index: 188

Text #1

Max Range: 5.0842. Min Range: -5.0842

Max Act: 4.8058. Min Act: -0.0000

Data Index: 965079 (The Pile)

Max Activating Token Index: 618

Text #2

Max Range: 5.0842. Min Range: -5.0842

Max Act: 4.5974. Min Act: -0.0000

Data Index: 1563708 (The Pile)

Max Activating Token Index: 232

Text #3

Max Range: 5.0842. Min Range: -5.0842

Max Act: 4.3247. Min Act: -0.0000

Data Index: 882287 (The Pile)

Max Activating Token Index: 679

Text #4

Max Range: 5.0842. Min Range: -5.0842

Max Act: 4.3551. Min Act: -0.0000

Data Index: 721690 (The Pile)

Max Activating Token Index: 441

Text #5

Max Range: 5.0842. Min Range: -5.0842

Max Act: 3.9794. Min Act: -0.0000

Data Index: 1719694 (The Pile)

Max Activating Token Index: 457

Text #6

Max Range: 5.0842. Min Range: -5.0842

Max Act: 4.1019. Min Act: -0.0000

Data Index: 1078707 (The Pile)

Max Activating Token Index: 388

Text #7

Max Range: 5.0842. Min Range: -5.0842

Max Act: 4.3968. Min Act: -0.0000

Data Index: 183732 (The Pile)

Max Activating Token Index: 784

Text #8

Max Range: 5.0842. Min Range: -5.0842

Max Act: 3.9893. Min Act: -0.0000

Data Index: 1473081 (The Pile)

Max Activating Token Index: 457

Text #9

Max Range: 5.0842. Min Range: -5.0842

Max Act: 4.2369. Min Act: -0.0000

Data Index: 1179189 (The Pile)

Max Activating Token Index: 646

Text #10

Max Range: 5.0842. Min Range: -5.0842

Max Act: 4.0826. Min Act: -0.0000

Data Index: 940387 (The Pile)

Max Activating Token Index: 583

Text #11

Max Range: 5.0842. Min Range: -5.0842

Max Act: 3.9799. Min Act: -0.0000

Data Index: 617862 (The Pile)

Max Activating Token Index: 145

Text #12

Max Range: 5.0842. Min Range: -5.0842

Max Act: 3.7846. Min Act: -0.0000

Data Index: 337432 (The Pile)

Max Activating Token Index: 534

Text #13

Max Range: 5.0842. Min Range: -5.0842

Max Act: 3.9359. Min Act: -0.0000

Data Index: 567312 (The Pile)

Max Activating Token Index: 970

Text #14

Max Range: 5.0842. Min Range: -5.0842

Max Act: 3.9376. Min Act: -0.0000

Data Index: 1727957 (The Pile)

Max Activating Token Index: 113

Text #15

Max Range: 5.0842. Min Range: -5.0842

Max Act: 4.1024. Min Act: -0.0000

Data Index: 468447 (The Pile)

Max Activating Token Index: 767

Text #16

Max Range: 5.0842. Min Range: -5.0842

Max Act: 3.8150. Min Act: -0.0000

Data Index: 1506753 (The Pile)

Max Activating Token Index: 528

Text #17

Max Range: 5.0842. Min Range: -5.0842

Max Act: 3.6873. Min Act: -0.0000

Data Index: 1164261 (The Pile)

Max Activating Token Index: 122

Text #18

Max Range: 5.0842. Min Range: -5.0842

Max Act: 3.8537. Min Act: -0.0000

Data Index: 1782810 (The Pile)

Max Activating Token Index: 1021

Text #19

Max Range: 5.0842. Min Range: -5.0842

Max Act: 3.7880. Min Act: -0.0000

Data Index: 191378 (The Pile)

Max Activating Token Index: 463