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

Dataset: The Pile

Neuron 705 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.1980. Min Range: -3.1980

Max Act: 3.1980. Min Act: -0.0000

Data Index: 1866158 (The Pile)

Max Activating Token Index: 842

Text #1

Max Range: 3.1980. Min Range: -3.1980

Max Act: 2.1122. Min Act: -0.0000

Data Index: 1014592 (The Pile)

Max Activating Token Index: 764

Text #2

Max Range: 3.1980. Min Range: -3.1980

Max Act: 2.3126. Min Act: -0.0000

Data Index: 400081 (The Pile)

Max Activating Token Index: 800

Text #3

Max Range: 3.1980. Min Range: -3.1980

Max Act: 2.2037. Min Act: -0.0000

Data Index: 549410 (The Pile)

Max Activating Token Index: 962

Text #4

Max Range: 3.1980. Min Range: -3.1980

Max Act: 1.9205. Min Act: -0.0000

Data Index: 322164 (The Pile)

Max Activating Token Index: 661

Text #5

Max Range: 3.1980. Min Range: -3.1980

Max Act: 1.9535. Min Act: -0.0000

Data Index: 1756326 (The Pile)

Max Activating Token Index: 427

Text #6

Max Range: 3.1980. Min Range: -3.1980

Max Act: 1.7199. Min Act: -0.0000

Data Index: 1690497 (The Pile)

Max Activating Token Index: 835

Text #7

Max Range: 3.1980. Min Range: -3.1980

Max Act: 1.7014. Min Act: -0.0000

Data Index: 1790640 (The Pile)

Max Activating Token Index: 399

Text #8

Max Range: 3.1980. Min Range: -3.1980

Max Act: 1.8680. Min Act: -0.0000

Data Index: 933971 (The Pile)

Max Activating Token Index: 658

Text #9

Max Range: 3.1980. Min Range: -3.1980

Max Act: 1.5908. Min Act: -0.0000

Data Index: 1468800 (The Pile)

Max Activating Token Index: 639

Text #10

Max Range: 3.1980. Min Range: -3.1980

Max Act: 1.6726. Min Act: -0.0000

Data Index: 1316415 (The Pile)

Max Activating Token Index: 650

Text #11

Max Range: 3.1980. Min Range: -3.1980

Max Act: 1.6867. Min Act: -0.0000

Data Index: 501482 (The Pile)

Max Activating Token Index: 125

Text #12

Max Range: 3.1980. Min Range: -3.1980

Max Act: 1.5815. Min Act: -0.0000

Data Index: 1141461 (The Pile)

Max Activating Token Index: 356

Text #13

Max Range: 3.1980. Min Range: -3.1980

Max Act: 1.9867. Min Act: -0.0000

Data Index: 573333 (The Pile)

Max Activating Token Index: 685

Text #14

Max Range: 3.1980. Min Range: -3.1980

Max Act: 1.6353. Min Act: -0.0000

Data Index: 537390 (The Pile)

Max Activating Token Index: 949

Text #15

Max Range: 3.1980. Min Range: -3.1980

Max Act: 1.5760. Min Act: -0.0000

Data Index: 691974 (The Pile)

Max Activating Token Index: 995

Text #16

Max Range: 3.1980. Min Range: -3.1980

Max Act: 1.4423. Min Act: -0.0000

Data Index: 1398382 (The Pile)

Max Activating Token Index: 281

Text #17

Max Range: 3.1980. Min Range: -3.1980

Max Act: 1.7420. Min Act: -0.0000

Data Index: 1268253 (The Pile)

Max Activating Token Index: 832

Text #18

Max Range: 3.1980. Min Range: -3.1980

Max Act: 1.5194. Min Act: -0.0000

Data Index: 267410 (The Pile)

Max Activating Token Index: 577

Text #19

Max Range: 3.1980. Min Range: -3.1980

Max Act: 1.3970. Min Act: -0.0000

Data Index: 751525 (The Pile)

Max Activating Token Index: 139