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

Dataset: The Pile

Neuron 2017 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.6747. Min Act: -0.0000

Data Index: 1432671 (The Pile)

Max Activating Token Index: 315

Text #1

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.6569. Min Act: -0.0000

Data Index: 1010071 (The Pile)

Max Activating Token Index: 357

Text #2

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.6507. Min Act: -0.0000

Data Index: 384373 (The Pile)

Max Activating Token Index: 121

Text #3

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.6951. Min Act: -0.0000

Data Index: 1868310 (The Pile)

Max Activating Token Index: 491

Text #4

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.6455. Min Act: -0.0000

Data Index: 657700 (The Pile)

Max Activating Token Index: 463

Text #5

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.6589. Min Act: -0.0000

Data Index: 345254 (The Pile)

Max Activating Token Index: 131

Text #6

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.6056. Min Act: -0.0000

Data Index: 574986 (The Pile)

Max Activating Token Index: 337

Text #7

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.6078. Min Act: -0.0000

Data Index: 1382133 (The Pile)

Max Activating Token Index: 434

Text #8

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.6213. Min Act: -0.0000

Data Index: 1372223 (The Pile)

Max Activating Token Index: 411

Text #9

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5984. Min Act: -0.0000

Data Index: 686458 (The Pile)

Max Activating Token Index: 310

Text #10

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5419. Min Act: -0.0000

Data Index: 873429 (The Pile)

Max Activating Token Index: 800

Text #11

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5563. Min Act: -0.0000

Data Index: 799306 (The Pile)

Max Activating Token Index: 135

Text #12

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5786. Min Act: -0.0000

Data Index: 1733296 (The Pile)

Max Activating Token Index: 416

Text #13

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5802. Min Act: -0.0000

Data Index: 1185462 (The Pile)

Max Activating Token Index: 68

Text #14

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5775. Min Act: -0.0000

Data Index: 1738128 (The Pile)

Max Activating Token Index: 154

Text #15

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5732. Min Act: -0.0000

Data Index: 114789 (The Pile)

Max Activating Token Index: 351

Text #16

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5716. Min Act: -0.0000

Data Index: 749349 (The Pile)

Max Activating Token Index: 98

Text #17

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5854. Min Act: -0.0000

Data Index: 1153108 (The Pile)

Max Activating Token Index: 433

Text #18

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5336. Min Act: -0.0000

Data Index: 1133172 (The Pile)

Max Activating Token Index: 130

Text #19

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5638. Min Act: -0.0000

Data Index: 1826021 (The Pile)

Max Activating Token Index: 369