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

Dataset: The Pile

Neuron 4117 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: 0.6365. Min Range: -0.6365

Max Act: 0.6365. Min Act: -0.0000

Data Index: 1807238 (The Pile)

Max Activating Token Index: 24

Text #1

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.5572. Min Act: -0.0000

Data Index: 1150355 (The Pile)

Max Activating Token Index: 608

Text #2

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.5465. Min Act: -0.0000

Data Index: 163587 (The Pile)

Max Activating Token Index: 938

Text #3

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.5488. Min Act: -0.0000

Data Index: 1496630 (The Pile)

Max Activating Token Index: 718

Text #4

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.5183. Min Act: -0.0000

Data Index: 413114 (The Pile)

Max Activating Token Index: 166

Text #5

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.5500. Min Act: -0.0000

Data Index: 1030086 (The Pile)

Max Activating Token Index: 604

Text #6

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.4899. Min Act: -0.0000

Data Index: 461511 (The Pile)

Max Activating Token Index: 343

Text #7

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.5208. Min Act: -0.0000

Data Index: 1739446 (The Pile)

Max Activating Token Index: 250

Text #8

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.5074. Min Act: -0.0000

Data Index: 201248 (The Pile)

Max Activating Token Index: 444

Text #9

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.5494. Min Act: -0.0000

Data Index: 1053606 (The Pile)

Max Activating Token Index: 522

Text #10

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.4205. Min Act: -0.0000

Data Index: 675208 (The Pile)

Max Activating Token Index: 811

Text #11

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.4878. Min Act: -0.0000

Data Index: 1961242 (The Pile)

Max Activating Token Index: 377

Text #12

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.5263. Min Act: -0.0000

Data Index: 583079 (The Pile)

Max Activating Token Index: 190

Text #13

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.4985. Min Act: -0.0000

Data Index: 953717 (The Pile)

Max Activating Token Index: 959

Text #14

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.4826. Min Act: -0.0000

Data Index: 69581 (The Pile)

Max Activating Token Index: 117

Text #15

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.5118. Min Act: -0.0000

Data Index: 1388802 (The Pile)

Max Activating Token Index: 794

Text #16

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.4829. Min Act: -0.0000

Data Index: 1674626 (The Pile)

Max Activating Token Index: 378

Text #17

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.4988. Min Act: -0.0000

Data Index: 615135 (The Pile)

Max Activating Token Index: 436

Text #18

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.4934. Min Act: -0.0000

Data Index: 701293 (The Pile)

Max Activating Token Index: 484

Text #19

Max Range: 0.6365. Min Range: -0.6365

Max Act: 0.4764. Min Act: -0.0000

Data Index: 162366 (The Pile)

Max Activating Token Index: 441