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

Dataset: The Pile

Neuron 187 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: 0.9297. Min Range: -0.9297

Max Act: 0.9297. Min Act: -0.0000

Data Index: 1954018 (The Pile)

Max Activating Token Index: 852

Text #1

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.8418. Min Act: -0.0000

Data Index: 1004067 (The Pile)

Max Activating Token Index: 256

Text #2

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.8207. Min Act: -0.0000

Data Index: 359064 (The Pile)

Max Activating Token Index: 83

Text #3

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6888. Min Act: -0.0000

Data Index: 1368005 (The Pile)

Max Activating Token Index: 724

Text #4

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.7731. Min Act: -0.0000

Data Index: 1431914 (The Pile)

Max Activating Token Index: 24

Text #5

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6519. Min Act: -0.0000

Data Index: 1030363 (The Pile)

Max Activating Token Index: 562

Text #6

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6938. Min Act: -0.0000

Data Index: 535143 (The Pile)

Max Activating Token Index: 407

Text #7

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6327. Min Act: -0.0000

Data Index: 1932831 (The Pile)

Max Activating Token Index: 612

Text #8

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.7079. Min Act: -0.0000

Data Index: 1559490 (The Pile)

Max Activating Token Index: 15

Text #9

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6207. Min Act: -0.0000

Data Index: 1850191 (The Pile)

Max Activating Token Index: 91

Text #10

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.7280. Min Act: -0.0000

Data Index: 131827 (The Pile)

Max Activating Token Index: 589

Text #11

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6719. Min Act: -0.0000

Data Index: 265913 (The Pile)

Max Activating Token Index: 106

Text #12

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6865. Min Act: -0.0000

Data Index: 436410 (The Pile)

Max Activating Token Index: 820

Text #13

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6482. Min Act: -0.0000

Data Index: 1685234 (The Pile)

Max Activating Token Index: 164

Text #14

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6436. Min Act: -0.0000

Data Index: 96453 (The Pile)

Max Activating Token Index: 608

Text #15

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6433. Min Act: -0.0000

Data Index: 1481020 (The Pile)

Max Activating Token Index: 666

Text #16

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6357. Min Act: -0.0000

Data Index: 823220 (The Pile)

Max Activating Token Index: 609

Text #17

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6718. Min Act: -0.0000

Data Index: 202015 (The Pile)

Max Activating Token Index: 560

Text #18

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6898. Min Act: -0.0000

Data Index: 455078 (The Pile)

Max Activating Token Index: 913

Text #19

Max Range: 0.9297. Min Range: -0.9297

Max Act: 0.6651. Min Act: -0.0000

Data Index: 1382381 (The Pile)

Max Activating Token Index: 782