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

Dataset: The Pile

Neuron 113 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.2796. Min Act: -0.0000

Data Index: 563858 (The Pile)

Max Activating Token Index: 466

Text #1

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.2966. Min Act: -0.0000

Data Index: 723039 (The Pile)

Max Activating Token Index: 538

Text #2

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.2652. Min Act: -0.0000

Data Index: 1866027 (The Pile)

Max Activating Token Index: 431

Text #3

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.2270. Min Act: -0.0000

Data Index: 138602 (The Pile)

Max Activating Token Index: 404

Text #4

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.1846. Min Act: -0.0000

Data Index: 1091511 (The Pile)

Max Activating Token Index: 796

Text #5

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.1910. Min Act: -0.0000

Data Index: 1817228 (The Pile)

Max Activating Token Index: 451

Text #6

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.1763. Min Act: -0.0000

Data Index: 408433 (The Pile)

Max Activating Token Index: 127

Text #7

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.2776. Min Act: -0.0000

Data Index: 1892017 (The Pile)

Max Activating Token Index: 952

Text #8

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.1609. Min Act: -0.0000

Data Index: 464908 (The Pile)

Max Activating Token Index: 14

Text #9

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.1123. Min Act: -0.0000

Data Index: 1518551 (The Pile)

Max Activating Token Index: 798

Text #10

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.1353. Min Act: -0.0000

Data Index: 1149621 (The Pile)

Max Activating Token Index: 884

Text #11

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.0229. Min Act: -0.0000

Data Index: 616319 (The Pile)

Max Activating Token Index: 791

Text #12

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.0816. Min Act: -0.0000

Data Index: 1526216 (The Pile)

Max Activating Token Index: 407

Text #13

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.1732. Min Act: -0.0000

Data Index: 672907 (The Pile)

Max Activating Token Index: 810

Text #14

Max Range: 1.2966. Min Range: -1.2966

Max Act: 0.8211. Min Act: -0.0000

Data Index: 1723082 (The Pile)

Max Activating Token Index: 558

Text #15

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.0712. Min Act: -0.0000

Data Index: 1739623 (The Pile)

Max Activating Token Index: 16

Text #16

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.0373. Min Act: -0.0000

Data Index: 948682 (The Pile)

Max Activating Token Index: 613

Text #17

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.0873. Min Act: -0.0000

Data Index: 943393 (The Pile)

Max Activating Token Index: 606

Text #18

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.0543. Min Act: -0.0000

Data Index: 1046821 (The Pile)

Max Activating Token Index: 334

Text #19

Max Range: 1.2966. Min Range: -1.2966

Max Act: 1.0923. Min Act: -0.0000

Data Index: 1140236 (The Pile)

Max Activating Token Index: 445