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

Dataset: The Pile

Neuron 2984 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.7651. Min Act: -0.0000

Data Index: 1289222 (The Pile)

Max Activating Token Index: 317

Text #1

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.7657. Min Act: -0.0000

Data Index: 1590389 (The Pile)

Max Activating Token Index: 563

Text #2

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.6966. Min Act: -0.0000

Data Index: 1419059 (The Pile)

Max Activating Token Index: 920

Text #3

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.7170. Min Act: -0.0000

Data Index: 1728991 (The Pile)

Max Activating Token Index: 934

Text #4

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.6897. Min Act: -0.0000

Data Index: 979425 (The Pile)

Max Activating Token Index: 438

Text #5

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.7109. Min Act: -0.0000

Data Index: 1685386 (The Pile)

Max Activating Token Index: 193

Text #6

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.6757. Min Act: -0.0000

Data Index: 1798207 (The Pile)

Max Activating Token Index: 156

Text #7

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.6531. Min Act: -0.0000

Data Index: 230963 (The Pile)

Max Activating Token Index: 647

Text #8

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.6838. Min Act: -0.0000

Data Index: 874919 (The Pile)

Max Activating Token Index: 379

Text #9

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.6975. Min Act: -0.0000

Data Index: 1038362 (The Pile)

Max Activating Token Index: 682

Text #10

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.6646. Min Act: -0.0000

Data Index: 432055 (The Pile)

Max Activating Token Index: 87

Text #11

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.6405. Min Act: -0.0000

Data Index: 1686465 (The Pile)

Max Activating Token Index: 258

Text #12

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.6427. Min Act: -0.0000

Data Index: 690393 (The Pile)

Max Activating Token Index: 71

Text #13

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.6321. Min Act: -0.0000

Data Index: 745873 (The Pile)

Max Activating Token Index: 202

Text #14

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.6769. Min Act: 0.0000

Data Index: 599485 (The Pile)

Max Activating Token Index: 11

Text #15

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.6110. Min Act: -0.0000

Data Index: 1350179 (The Pile)

Max Activating Token Index: 911

Text #16

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.6811. Min Act: -0.0000

Data Index: 1013851 (The Pile)

Max Activating Token Index: 709

Text #17

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.6300. Min Act: -0.0000

Data Index: 834688 (The Pile)

Max Activating Token Index: 600

Text #18

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.6445. Min Act: -0.0000

Data Index: 1023961 (The Pile)

Max Activating Token Index: 463

Text #19

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.6263. Min Act: -0.0000

Data Index: 510524 (The Pile)

Max Activating Token Index: 322