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

Dataset: The Pile

Neuron 3620 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: 1.0976. Min Range: -1.0976

Max Act: 1.0428. Min Act: -0.0000

Data Index: 1369604 (The Pile)

Max Activating Token Index: 325

Text #1

Max Range: 1.0976. Min Range: -1.0976

Max Act: 1.0976. Min Act: -0.0000

Data Index: 597579 (The Pile)

Max Activating Token Index: 881

Text #2

Max Range: 1.0976. Min Range: -1.0976

Max Act: 1.0580. Min Act: -0.0000

Data Index: 791777 (The Pile)

Max Activating Token Index: 677

Text #3

Max Range: 1.0976. Min Range: -1.0976

Max Act: 0.9680. Min Act: -0.0000

Data Index: 1575527 (The Pile)

Max Activating Token Index: 299

Text #4

Max Range: 1.0976. Min Range: -1.0976

Max Act: 0.9312. Min Act: -0.0000

Data Index: 1554787 (The Pile)

Max Activating Token Index: 849

Text #5

Max Range: 1.0976. Min Range: -1.0976

Max Act: 1.0071. Min Act: -0.0000

Data Index: 699816 (The Pile)

Max Activating Token Index: 408

Text #6

Max Range: 1.0976. Min Range: -1.0976

Max Act: 0.9583. Min Act: -0.0000

Data Index: 1291778 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 1.0976. Min Range: -1.0976

Max Act: 0.9157. Min Act: -0.0000

Data Index: 1201806 (The Pile)

Max Activating Token Index: 831

Text #8

Max Range: 1.0976. Min Range: -1.0976

Max Act: 0.8687. Min Act: -0.0000

Data Index: 902243 (The Pile)

Max Activating Token Index: 970

Text #9

Max Range: 1.0976. Min Range: -1.0976

Max Act: 0.9218. Min Act: 0.0000

Data Index: 1059110 (The Pile)

Max Activating Token Index: 819

Text #10

Max Range: 1.0976. Min Range: -1.0976

Max Act: 0.9142. Min Act: -0.0000

Data Index: 1507468 (The Pile)

Max Activating Token Index: 866

Text #11

Max Range: 1.0976. Min Range: -1.0976

Max Act: 0.8890. Min Act: -0.0000

Data Index: 620522 (The Pile)

Max Activating Token Index: 546

Text #12

Max Range: 1.0976. Min Range: -1.0976

Max Act: 0.8557. Min Act: -0.0000

Data Index: 1605982 (The Pile)

Max Activating Token Index: 805

Text #13

Max Range: 1.0976. Min Range: -1.0976

Max Act: 0.8923. Min Act: -0.0000

Data Index: 356171 (The Pile)

Max Activating Token Index: 317

Text #14

Max Range: 1.0976. Min Range: -1.0976

Max Act: 0.8356. Min Act: -0.0000

Data Index: 248406 (The Pile)

Max Activating Token Index: 342

Text #15

Max Range: 1.0976. Min Range: -1.0976

Max Act: 0.7645. Min Act: -0.0000

Data Index: 1674064 (The Pile)

Max Activating Token Index: 51

Text #16

Max Range: 1.0976. Min Range: -1.0976

Max Act: 0.7728. Min Act: -0.0000

Data Index: 1019554 (The Pile)

Max Activating Token Index: 550

Text #17

Max Range: 1.0976. Min Range: -1.0976

Max Act: 0.7508. Min Act: -0.0000

Data Index: 518810 (The Pile)

Max Activating Token Index: 628

Text #18

Max Range: 1.0976. Min Range: -1.0976

Max Act: 0.7795. Min Act: -0.0000

Data Index: 1478752 (The Pile)

Max Activating Token Index: 802

Text #19

Max Range: 1.0976. Min Range: -1.0976

Max Act: 0.8028. Min Act: -0.0000

Data Index: 1086047 (The Pile)

Max Activating Token Index: 996