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

Dataset: The Pile

Neuron 4455 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0723. Min Range: -1.0723

Max Act: 1.0723. Min Act: -0.0000

Data Index: 1312660 (The Pile)

Max Activating Token Index: 101

Text #1

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.8615. Min Act: -0.0000

Data Index: 695037 (The Pile)

Max Activating Token Index: 750

Text #2

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.8549. Min Act: -0.0000

Data Index: 1956553 (The Pile)

Max Activating Token Index: 384

Text #3

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.7150. Min Act: -0.0000

Data Index: 1480671 (The Pile)

Max Activating Token Index: 687

Text #4

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.7563. Min Act: -0.0000

Data Index: 35731 (The Pile)

Max Activating Token Index: 845

Text #5

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.7465. Min Act: -0.0000

Data Index: 1542903 (The Pile)

Max Activating Token Index: 91

Text #6

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.7117. Min Act: -0.0000

Data Index: 1458162 (The Pile)

Max Activating Token Index: 753

Text #7

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.8387. Min Act: -0.0000

Data Index: 980765 (The Pile)

Max Activating Token Index: 798

Text #8

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.7299. Min Act: -0.0000

Data Index: 927197 (The Pile)

Max Activating Token Index: 583

Text #9

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.7135. Min Act: -0.0000

Data Index: 616685 (The Pile)

Max Activating Token Index: 319

Text #10

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.7159. Min Act: -0.0000

Data Index: 1260983 (The Pile)

Max Activating Token Index: 447

Text #11

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.7167. Min Act: -0.0000

Data Index: 497015 (The Pile)

Max Activating Token Index: 505

Text #12

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.7201. Min Act: -0.0000

Data Index: 1096579 (The Pile)

Max Activating Token Index: 484

Text #13

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.7354. Min Act: -0.0000

Data Index: 264913 (The Pile)

Max Activating Token Index: 538

Text #14

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.7357. Min Act: -0.0000

Data Index: 637229 (The Pile)

Max Activating Token Index: 119

Text #15

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.6953. Min Act: -0.0000

Data Index: 1009494 (The Pile)

Max Activating Token Index: 749

Text #16

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.6936. Min Act: -0.0000

Data Index: 1045 (The Pile)

Max Activating Token Index: 60

Text #17

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.6797. Min Act: -0.0000

Data Index: 625592 (The Pile)

Max Activating Token Index: 357

Text #18

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.7158. Min Act: -0.0000

Data Index: 1758839 (The Pile)

Max Activating Token Index: 413

Text #19

Max Range: 1.0723. Min Range: -1.0723

Max Act: 0.6514. Min Act: -0.0000

Data Index: 621649 (The Pile)

Max Activating Token Index: 455