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

Dataset: The Pile

Neuron 4788 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: 1.1503. Min Range: -1.1503

Max Act: 1.1405. Min Act: -0.0000

Data Index: 460015 (The Pile)

Max Activating Token Index: 236

Text #1

Max Range: 1.1503. Min Range: -1.1503

Max Act: 1.1149. Min Act: -0.0000

Data Index: 412179 (The Pile)

Max Activating Token Index: 130

Text #2

Max Range: 1.1503. Min Range: -1.1503

Max Act: 1.1503. Min Act: -0.0000

Data Index: 597970 (The Pile)

Max Activating Token Index: 403

Text #3

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.9839. Min Act: -0.0000

Data Index: 1504599 (The Pile)

Max Activating Token Index: 227

Text #4

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.9168. Min Act: -0.0000

Data Index: 1514873 (The Pile)

Max Activating Token Index: 522

Text #5

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.9605. Min Act: -0.0000

Data Index: 1734235 (The Pile)

Max Activating Token Index: 573

Text #6

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.9960. Min Act: -0.0000

Data Index: 176915 (The Pile)

Max Activating Token Index: 83

Text #7

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.8647. Min Act: -0.0000

Data Index: 1568844 (The Pile)

Max Activating Token Index: 874

Text #8

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.9852. Min Act: -0.0000

Data Index: 1985451 (The Pile)

Max Activating Token Index: 367

Text #9

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.7950. Min Act: -0.0000

Data Index: 1206805 (The Pile)

Max Activating Token Index: 698

Text #10

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.9447. Min Act: -0.0000

Data Index: 1362613 (The Pile)

Max Activating Token Index: 221

Text #11

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.8920. Min Act: -0.0000

Data Index: 1177773 (The Pile)

Max Activating Token Index: 559

Text #12

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.8919. Min Act: -0.0000

Data Index: 277763 (The Pile)

Max Activating Token Index: 342

Text #13

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.9687. Min Act: -0.0000

Data Index: 530919 (The Pile)

Max Activating Token Index: 753

Text #14

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.8338. Min Act: -0.0000

Data Index: 760007 (The Pile)

Max Activating Token Index: 260

Text #15

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.8371. Min Act: -0.0000

Data Index: 1756698 (The Pile)

Max Activating Token Index: 102

Text #16

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.7397. Min Act: -0.0000

Data Index: 526861 (The Pile)

Max Activating Token Index: 765

Text #17

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.8821. Min Act: -0.0000

Data Index: 827744 (The Pile)

Max Activating Token Index: 458

Text #18

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.8507. Min Act: -0.0000

Data Index: 1920439 (The Pile)

Max Activating Token Index: 432

Text #19

Max Range: 1.1503. Min Range: -1.1503

Max Act: 0.8324. Min Act: -0.0000

Data Index: 1518747 (The Pile)

Max Activating Token Index: 833