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

Dataset: The Pile

Neuron 753 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.6782. Min Act: -0.0000

Data Index: 1565396 (The Pile)

Max Activating Token Index: 13

Text #1

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.3602. Min Act: -0.0000

Data Index: 464024 (The Pile)

Max Activating Token Index: 323

Text #2

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.3427. Min Act: -0.0000

Data Index: 1460198 (The Pile)

Max Activating Token Index: 520

Text #3

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.3430. Min Act: -0.0000

Data Index: 1016935 (The Pile)

Max Activating Token Index: 106

Text #4

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.3219. Min Act: -0.0000

Data Index: 1862630 (The Pile)

Max Activating Token Index: 238

Text #5

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.3343. Min Act: -0.0000

Data Index: 411900 (The Pile)

Max Activating Token Index: 568

Text #6

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.3197. Min Act: -0.0000

Data Index: 1336795 (The Pile)

Max Activating Token Index: 116

Text #7

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.3554. Min Act: -0.0000

Data Index: 971937 (The Pile)

Max Activating Token Index: 851

Text #8

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.3105. Min Act: -0.0000

Data Index: 995052 (The Pile)

Max Activating Token Index: 304

Text #9

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.3430. Min Act: -0.0000

Data Index: 1789860 (The Pile)

Max Activating Token Index: 142

Text #10

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.3171. Min Act: -0.0000

Data Index: 1034164 (The Pile)

Max Activating Token Index: 24

Text #11

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.3064. Min Act: -0.0000

Data Index: 1162418 (The Pile)

Max Activating Token Index: 424

Text #12

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.2950. Min Act: -0.0000

Data Index: 814411 (The Pile)

Max Activating Token Index: 138

Text #13

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.3318. Min Act: -0.0000

Data Index: 510611 (The Pile)

Max Activating Token Index: 298

Text #14

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.2887. Min Act: -0.0000

Data Index: 1820221 (The Pile)

Max Activating Token Index: 7

Text #15

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.3200. Min Act: -0.0000

Data Index: 444156 (The Pile)

Max Activating Token Index: 663

Text #16

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.3111. Min Act: -0.0000

Data Index: 28911 (The Pile)

Max Activating Token Index: 467

Text #17

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.2983. Min Act: -0.0000

Data Index: 664067 (The Pile)

Max Activating Token Index: 913

Text #18

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.2706. Min Act: -0.0000

Data Index: 290754 (The Pile)

Max Activating Token Index: 182

Text #19

Max Range: 0.6782. Min Range: -0.6782

Max Act: 0.2881. Min Act: -0.0000

Data Index: 1599629 (The Pile)

Max Activating Token Index: 236