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

Dataset: The Pile

Neuron 2890 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0556. Min Range: -1.0556

Max Act: 1.0556. Min Act: -0.0000

Data Index: 417617 (The Pile)

Max Activating Token Index: 274

Text #1

Max Range: 1.0556. Min Range: -1.0556

Max Act: 0.9434. Min Act: -0.0000

Data Index: 692590 (The Pile)

Max Activating Token Index: 624

Text #2

Max Range: 1.0556. Min Range: -1.0556

Max Act: 0.8497. Min Act: -0.0000

Data Index: 290284 (The Pile)

Max Activating Token Index: 830

Text #3

Max Range: 1.0556. Min Range: -1.0556

Max Act: 0.8259. Min Act: -0.0000

Data Index: 1602855 (The Pile)

Max Activating Token Index: 1020

Text #4

Max Range: 1.0556. Min Range: -1.0556

Max Act: 0.7944. Min Act: -0.0000

Data Index: 874269 (The Pile)

Max Activating Token Index: 683

Text #5

Max Range: 1.0556. Min Range: -1.0556

Max Act: 0.7451. Min Act: -0.0000

Data Index: 265397 (The Pile)

Max Activating Token Index: 377

Text #6

Max Range: 1.0556. Min Range: -1.0556

Max Act: 0.6921. Min Act: -0.0000

Data Index: 769859 (The Pile)

Max Activating Token Index: 179

Text #7

Max Range: 1.0556. Min Range: -1.0556

Max Act: 0.5984. Min Act: -0.0000

Data Index: 281952 (The Pile)

Max Activating Token Index: 965

Text #8

Max Range: 1.0556. Min Range: -1.0556

Max Act: 0.6625. Min Act: -0.0000

Data Index: 484985 (The Pile)

Max Activating Token Index: 332

Text #9

Max Range: 1.0556. Min Range: -1.0556

Max Act: 0.6398. Min Act: -0.0000

Data Index: 195791 (The Pile)

Max Activating Token Index: 616

Text #10

Max Range: 1.0556. Min Range: -1.0556

Max Act: 0.6398. Min Act: -0.0000

Data Index: 4178 (The Pile)

Max Activating Token Index: 461

Text #11

Max Range: 1.0556. Min Range: -1.0556

Max Act: 0.6121. Min Act: -0.0000

Data Index: 573130 (The Pile)

Max Activating Token Index: 32

Text #12

Max Range: 1.0556. Min Range: -1.0556

Max Act: 0.5939. Min Act: -0.0000

Data Index: 839224 (The Pile)

Max Activating Token Index: 585

Text #13

Max Range: 1.0556. Min Range: -1.0556

Max Act: 0.6513. Min Act: -0.0000

Data Index: 1687512 (The Pile)

Max Activating Token Index: 60

Text #14

Max Range: 1.0556. Min Range: -1.0556

Max Act: 0.5526. Min Act: -0.0000

Data Index: 920742 (The Pile)

Max Activating Token Index: 433

Text #15

Max Range: 1.0556. Min Range: -1.0556

Max Act: 0.6219. Min Act: -0.0000

Data Index: 570090 (The Pile)

Max Activating Token Index: 393

Text #16

Max Range: 1.0556. Min Range: -1.0556

Max Act: 0.5709. Min Act: -0.0000

Data Index: 1844444 (The Pile)

Max Activating Token Index: 256

Text #17

Max Range: 1.0556. Min Range: -1.0556

Max Act: 0.5425. Min Act: -0.0000

Data Index: 1962746 (The Pile)

Max Activating Token Index: 126

Text #18

Max Range: 1.0556. Min Range: -1.0556

Max Act: 0.5322. Min Act: -0.0000

Data Index: 3676 (The Pile)

Max Activating Token Index: 458

Text #19

Max Range: 1.0556. Min Range: -1.0556

Max Act: 0.5507. Min Act: -0.0000

Data Index: 708075 (The Pile)

Max Activating Token Index: 161