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

Dataset: The Pile

Neuron 1702 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: 0.9343. Min Range: -0.9343

Max Act: 0.9343. Min Act: -0.0000

Data Index: 1500926 (The Pile)

Max Activating Token Index: 565

Text #1

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.9145. Min Act: -0.0000

Data Index: 1591710 (The Pile)

Max Activating Token Index: 494

Text #2

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.8875. Min Act: -0.0000

Data Index: 1669649 (The Pile)

Max Activating Token Index: 912

Text #3

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.8790. Min Act: -0.0000

Data Index: 192751 (The Pile)

Max Activating Token Index: 232

Text #4

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.9270. Min Act: -0.0000

Data Index: 232426 (The Pile)

Max Activating Token Index: 284

Text #5

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.8257. Min Act: -0.0000

Data Index: 1784930 (The Pile)

Max Activating Token Index: 331

Text #6

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.8496. Min Act: -0.0000

Data Index: 1486428 (The Pile)

Max Activating Token Index: 440

Text #7

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.8678. Min Act: -0.0000

Data Index: 874759 (The Pile)

Max Activating Token Index: 967

Text #8

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.8412. Min Act: -0.0000

Data Index: 233142 (The Pile)

Max Activating Token Index: 667

Text #9

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.7441. Min Act: -0.0000

Data Index: 603082 (The Pile)

Max Activating Token Index: 1011

Text #10

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.7965. Min Act: -0.0000

Data Index: 988708 (The Pile)

Max Activating Token Index: 985

Text #11

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.7791. Min Act: -0.0000

Data Index: 118304 (The Pile)

Max Activating Token Index: 716

Text #12

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.7971. Min Act: -0.0000

Data Index: 1557790 (The Pile)

Max Activating Token Index: 582

Text #13

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.8075. Min Act: -0.0000

Data Index: 1791948 (The Pile)

Max Activating Token Index: 258

Text #14

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.7600. Min Act: -0.0000

Data Index: 220707 (The Pile)

Max Activating Token Index: 948

Text #15

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.7558. Min Act: -0.0000

Data Index: 945283 (The Pile)

Max Activating Token Index: 837

Text #16

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.7677. Min Act: -0.0000

Data Index: 649232 (The Pile)

Max Activating Token Index: 64

Text #17

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.7348. Min Act: -0.0000

Data Index: 205664 (The Pile)

Max Activating Token Index: 334

Text #18

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.7574. Min Act: -0.0000

Data Index: 145641 (The Pile)

Max Activating Token Index: 441

Text #19

Max Range: 0.9343. Min Range: -0.9343

Max Act: 0.7717. Min Act: -0.0000

Data Index: 271065 (The Pile)

Max Activating Token Index: 514