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

Dataset: The Pile

Neuron 610 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5637. Min Range: -3.5637

Max Act: 3.5637. Min Act: 0.0000

Data Index: 385966 (The Pile)

Max Activating Token Index: 454

Text #1

Max Range: 3.5637. Min Range: -3.5637

Max Act: 3.0984. Min Act: -0.0000

Data Index: 786805 (The Pile)

Max Activating Token Index: 715

Text #2

Max Range: 3.5637. Min Range: -3.5637

Max Act: 3.2506. Min Act: -0.0000

Data Index: 514967 (The Pile)

Max Activating Token Index: 444

Text #3

Max Range: 3.5637. Min Range: -3.5637

Max Act: 2.9946. Min Act: -0.0000

Data Index: 798410 (The Pile)

Max Activating Token Index: 119

Text #4

Max Range: 3.5637. Min Range: -3.5637

Max Act: 2.9503. Min Act: -0.0000

Data Index: 997147 (The Pile)

Max Activating Token Index: 77

Text #5

Max Range: 3.5637. Min Range: -3.5637

Max Act: 2.8044. Min Act: -0.0000

Data Index: 499751 (The Pile)

Max Activating Token Index: 761

Text #6

Max Range: 3.5637. Min Range: -3.5637

Max Act: 2.3977. Min Act: -0.0000

Data Index: 1849475 (The Pile)

Max Activating Token Index: 851

Text #7

Max Range: 3.5637. Min Range: -3.5637

Max Act: 2.8706. Min Act: -0.0000

Data Index: 303353 (The Pile)

Max Activating Token Index: 475

Text #8

Max Range: 3.5637. Min Range: -3.5637

Max Act: 2.7406. Min Act: -0.0000

Data Index: 315384 (The Pile)

Max Activating Token Index: 91

Text #9

Max Range: 3.5637. Min Range: -3.5637

Max Act: 2.5618. Min Act: -0.0000

Data Index: 1358998 (The Pile)

Max Activating Token Index: 143

Text #10

Max Range: 3.5637. Min Range: -3.5637

Max Act: 2.5097. Min Act: -0.0000

Data Index: 1771506 (The Pile)

Max Activating Token Index: 408

Text #11

Max Range: 3.5637. Min Range: -3.5637

Max Act: 2.7483. Min Act: -0.0000

Data Index: 906886 (The Pile)

Max Activating Token Index: 994

Text #12

Max Range: 3.5637. Min Range: -3.5637

Max Act: 2.6336. Min Act: 0.0000

Data Index: 365948 (The Pile)

Max Activating Token Index: 874

Text #13

Max Range: 3.5637. Min Range: -3.5637

Max Act: 2.5645. Min Act: -0.0000

Data Index: 1211178 (The Pile)

Max Activating Token Index: 977

Text #14

Max Range: 3.5637. Min Range: -3.5637

Max Act: 2.4219. Min Act: -0.0000

Data Index: 632904 (The Pile)

Max Activating Token Index: 617

Text #15

Max Range: 3.5637. Min Range: -3.5637

Max Act: 2.5274. Min Act: -0.0000

Data Index: 31431 (The Pile)

Max Activating Token Index: 116

Text #16

Max Range: 3.5637. Min Range: -3.5637

Max Act: 2.7721. Min Act: -0.0000

Data Index: 1874313 (The Pile)

Max Activating Token Index: 687

Text #17

Max Range: 3.5637. Min Range: -3.5637

Max Act: 2.7783. Min Act: -0.0000

Data Index: 479485 (The Pile)

Max Activating Token Index: 538

Text #18

Max Range: 3.5637. Min Range: -3.5637

Max Act: 2.5063. Min Act: -0.0000

Data Index: 547972 (The Pile)

Max Activating Token Index: 247

Text #19

Max Range: 3.5637. Min Range: -3.5637

Max Act: 2.2235. Min Act: -0.0000

Data Index: 652690 (The Pile)

Max Activating Token Index: 884