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

Dataset: The Pile

Neuron 4327 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: 0.7613. Min Range: -0.7613

Max Act: 0.7356. Min Act: -0.0000

Data Index: 21034 (The Pile)

Max Activating Token Index: 284

Text #1

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.7613. Min Act: -0.0000

Data Index: 1908414 (The Pile)

Max Activating Token Index: 542

Text #2

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.6048. Min Act: -0.0000

Data Index: 722246 (The Pile)

Max Activating Token Index: 774

Text #3

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.7258. Min Act: -0.0000

Data Index: 235443 (The Pile)

Max Activating Token Index: 413

Text #4

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.6072. Min Act: -0.0000

Data Index: 1116134 (The Pile)

Max Activating Token Index: 576

Text #5

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5900. Min Act: -0.0000

Data Index: 1095780 (The Pile)

Max Activating Token Index: 327

Text #6

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5858. Min Act: -0.0000

Data Index: 1582833 (The Pile)

Max Activating Token Index: 409

Text #7

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.6407. Min Act: -0.0000

Data Index: 1130630 (The Pile)

Max Activating Token Index: 240

Text #8

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5494. Min Act: -0.0000

Data Index: 1235911 (The Pile)

Max Activating Token Index: 632

Text #9

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5654. Min Act: -0.0000

Data Index: 1225145 (The Pile)

Max Activating Token Index: 489

Text #10

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5503. Min Act: -0.0000

Data Index: 964405 (The Pile)

Max Activating Token Index: 117

Text #11

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5029. Min Act: -0.0000

Data Index: 23663 (The Pile)

Max Activating Token Index: 539

Text #12

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5871. Min Act: -0.0000

Data Index: 1963576 (The Pile)

Max Activating Token Index: 51

Text #13

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5079. Min Act: -0.0000

Data Index: 1555085 (The Pile)

Max Activating Token Index: 726

Text #14

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5226. Min Act: -0.0000

Data Index: 683576 (The Pile)

Max Activating Token Index: 664

Text #15

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.4993. Min Act: -0.0000

Data Index: 16615 (The Pile)

Max Activating Token Index: 296

Text #16

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5496. Min Act: -0.0000

Data Index: 465384 (The Pile)

Max Activating Token Index: 456

Text #17

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.4696. Min Act: -0.0000

Data Index: 1011790 (The Pile)

Max Activating Token Index: 328

Text #18

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5059. Min Act: -0.0000

Data Index: 1316629 (The Pile)

Max Activating Token Index: 726

Text #19

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5187. Min Act: -0.0000

Data Index: 681895 (The Pile)

Max Activating Token Index: 152