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

Dataset: The Pile

Neuron 1637 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: 1.0779. Min Range: -1.0779

Max Act: 1.0779. Min Act: -0.0000

Data Index: 1078798 (The Pile)

Max Activating Token Index: 822

Text #1

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.8869. Min Act: -0.0000

Data Index: 133881 (The Pile)

Max Activating Token Index: 168

Text #2

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.8141. Min Act: -0.0000

Data Index: 849015 (The Pile)

Max Activating Token Index: 983

Text #3

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.7965. Min Act: -0.0000

Data Index: 829335 (The Pile)

Max Activating Token Index: 858

Text #4

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.7595. Min Act: -0.0000

Data Index: 357517 (The Pile)

Max Activating Token Index: 707

Text #5

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.7906. Min Act: -0.0000

Data Index: 1745520 (The Pile)

Max Activating Token Index: 663

Text #6

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.8206. Min Act: -0.0000

Data Index: 1878882 (The Pile)

Max Activating Token Index: 582

Text #7

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.7251. Min Act: -0.0000

Data Index: 1435087 (The Pile)

Max Activating Token Index: 383

Text #8

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.7380. Min Act: -0.0000

Data Index: 116036 (The Pile)

Max Activating Token Index: 264

Text #9

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.7464. Min Act: -0.0000

Data Index: 1923907 (The Pile)

Max Activating Token Index: 241

Text #10

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.7200. Min Act: -0.0000

Data Index: 1785837 (The Pile)

Max Activating Token Index: 871

Text #11

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.6948. Min Act: -0.0000

Data Index: 1085091 (The Pile)

Max Activating Token Index: 338

Text #12

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.6927. Min Act: -0.0000

Data Index: 885288 (The Pile)

Max Activating Token Index: 494

Text #13

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.6819. Min Act: -0.0000

Data Index: 601109 (The Pile)

Max Activating Token Index: 733

Text #14

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.7123. Min Act: -0.0000

Data Index: 986374 (The Pile)

Max Activating Token Index: 404

Text #15

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.6689. Min Act: -0.0000

Data Index: 1577236 (The Pile)

Max Activating Token Index: 697

Text #16

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.7219. Min Act: -0.0000

Data Index: 1428341 (The Pile)

Max Activating Token Index: 480

Text #17

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.6959. Min Act: -0.0000

Data Index: 875435 (The Pile)

Max Activating Token Index: 392

Text #18

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.6787. Min Act: -0.0000

Data Index: 763046 (The Pile)

Max Activating Token Index: 945

Text #19

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.6608. Min Act: -0.0000

Data Index: 438272 (The Pile)

Max Activating Token Index: 591