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

Dataset: The Pile

Neuron 1378 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.4868. Min Act: -0.0001

Data Index: 1197819 (The Pile)

Max Activating Token Index: 757

Text #1

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.4568. Min Act: -0.0000

Data Index: 393336 (The Pile)

Max Activating Token Index: 895

Text #2

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.4351. Min Act: -0.0000

Data Index: 1399176 (The Pile)

Max Activating Token Index: 990

Text #3

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.4318. Min Act: -0.0001

Data Index: 796006 (The Pile)

Max Activating Token Index: 152

Text #4

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3928. Min Act: -0.0000

Data Index: 1620129 (The Pile)

Max Activating Token Index: 555

Text #5

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.4106. Min Act: -0.0000

Data Index: 1484702 (The Pile)

Max Activating Token Index: 1007

Text #6

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3935. Min Act: -0.0000

Data Index: 1200377 (The Pile)

Max Activating Token Index: 525

Text #7

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3918. Min Act: -0.0000

Data Index: 1301824 (The Pile)

Max Activating Token Index: 249

Text #8

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.4024. Min Act: -0.0000

Data Index: 1944117 (The Pile)

Max Activating Token Index: 466

Text #9

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3877. Min Act: -0.0000

Data Index: 1980151 (The Pile)

Max Activating Token Index: 278

Text #10

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3948. Min Act: -0.0000

Data Index: 1959475 (The Pile)

Max Activating Token Index: 115

Text #11

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3561. Min Act: -0.0000

Data Index: 1620243 (The Pile)

Max Activating Token Index: 241

Text #12

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3689. Min Act: -0.0000

Data Index: 1612509 (The Pile)

Max Activating Token Index: 978

Text #13

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3863. Min Act: -0.0000

Data Index: 183577 (The Pile)

Max Activating Token Index: 388

Text #14

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3737. Min Act: -0.0000

Data Index: 334547 (The Pile)

Max Activating Token Index: 930

Text #15

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3993. Min Act: -0.0000

Data Index: 1652419 (The Pile)

Max Activating Token Index: 586

Text #16

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.5065. Min Act: -0.0000

Data Index: 251917 (The Pile)

Max Activating Token Index: 567

Text #17

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3592. Min Act: -0.0000

Data Index: 1175987 (The Pile)

Max Activating Token Index: 683

Text #18

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.3664. Min Act: -0.0000

Data Index: 1553312 (The Pile)

Max Activating Token Index: 921

Text #19

Max Range: 0.5065. Min Range: -0.5065

Max Act: 0.4314. Min Act: -0.0000

Data Index: 916132 (The Pile)

Max Activating Token Index: 869