Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3519 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.1800. Min Act: -0.0000

Data Index: 458008 (The Pile)

Max Activating Token Index: 518

Text #1

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.1584. Min Act: -0.0000

Data Index: 761982 (The Pile)

Max Activating Token Index: 394

Text #2

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.4067. Min Act: -0.0000

Data Index: 251828 (The Pile)

Max Activating Token Index: 451

Text #3

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.3068. Min Act: -0.0000

Data Index: 1343790 (The Pile)

Max Activating Token Index: 888

Text #4

Max Range: 3.4067. Min Range: -3.4067

Max Act: 2.9789. Min Act: -0.0000

Data Index: 1925223 (The Pile)

Max Activating Token Index: 402

Text #5

Max Range: 3.4067. Min Range: -3.4067

Max Act: 2.8458. Min Act: -0.0000

Data Index: 1933914 (The Pile)

Max Activating Token Index: 376

Text #6

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.0328. Min Act: -0.0000

Data Index: 404944 (The Pile)

Max Activating Token Index: 294

Text #7

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.1347. Min Act: -0.0000

Data Index: 748445 (The Pile)

Max Activating Token Index: 484

Text #8

Max Range: 3.4067. Min Range: -3.4067

Max Act: 2.8543. Min Act: -0.0000

Data Index: 1212087 (The Pile)

Max Activating Token Index: 764

Text #9

Max Range: 3.4067. Min Range: -3.4067

Max Act: 2.9641. Min Act: -0.0000

Data Index: 1338549 (The Pile)

Max Activating Token Index: 666

Text #10

Max Range: 3.4067. Min Range: -3.4067

Max Act: 2.8335. Min Act: -0.0000

Data Index: 134419 (The Pile)

Max Activating Token Index: 331

Text #11

Max Range: 3.4067. Min Range: -3.4067

Max Act: 2.8354. Min Act: -0.0000

Data Index: 783434 (The Pile)

Max Activating Token Index: 731

Text #12

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.1063. Min Act: -0.0000

Data Index: 29386 (The Pile)

Max Activating Token Index: 526

Text #13

Max Range: 3.4067. Min Range: -3.4067

Max Act: 2.7061. Min Act: -0.0000

Data Index: 816306 (The Pile)

Max Activating Token Index: 969

Text #14

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.0430. Min Act: -0.0000

Data Index: 1114392 (The Pile)

Max Activating Token Index: 433

Text #15

Max Range: 3.4067. Min Range: -3.4067

Max Act: 2.6963. Min Act: -0.0000

Data Index: 866768 (The Pile)

Max Activating Token Index: 253

Text #16

Max Range: 3.4067. Min Range: -3.4067

Max Act: 3.1711. Min Act: -0.0000

Data Index: 824236 (The Pile)

Max Activating Token Index: 654

Text #17

Max Range: 3.4067. Min Range: -3.4067

Max Act: 2.6775. Min Act: -0.0000

Data Index: 1660200 (The Pile)

Max Activating Token Index: 392

Text #18

Max Range: 3.4067. Min Range: -3.4067

Max Act: 2.6798. Min Act: -0.0000

Data Index: 1585264 (The Pile)

Max Activating Token Index: 695

Text #19

Max Range: 3.4067. Min Range: -3.4067

Max Act: 2.6161. Min Act: -0.0000

Data Index: 1180568 (The Pile)

Max Activating Token Index: 888