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

Dataset: The Pile

Neuron 424 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: 7.4421. Min Range: -7.4421

Max Act: 7.4421. Min Act: -0.0000

Data Index: 966288 (The Pile)

Max Activating Token Index: 518

Text #1

Max Range: 7.4421. Min Range: -7.4421

Max Act: 6.3416. Min Act: -0.0000

Data Index: 815579 (The Pile)

Max Activating Token Index: 646

Text #2

Max Range: 7.4421. Min Range: -7.4421

Max Act: 6.4726. Min Act: -0.0000

Data Index: 992848 (The Pile)

Max Activating Token Index: 958

Text #3

Max Range: 7.4421. Min Range: -7.4421

Max Act: 6.6780. Min Act: -0.0000

Data Index: 1842207 (The Pile)

Max Activating Token Index: 698

Text #4

Max Range: 7.4421. Min Range: -7.4421

Max Act: 7.1667. Min Act: -0.0000

Data Index: 1520773 (The Pile)

Max Activating Token Index: 987

Text #5

Max Range: 7.4421. Min Range: -7.4421

Max Act: 6.3687. Min Act: -0.0000

Data Index: 1751875 (The Pile)

Max Activating Token Index: 715

Text #6

Max Range: 7.4421. Min Range: -7.4421

Max Act: 6.5923. Min Act: -0.0000

Data Index: 1045182 (The Pile)

Max Activating Token Index: 710

Text #7

Max Range: 7.4421. Min Range: -7.4421

Max Act: 6.1370. Min Act: -0.0000

Data Index: 324720 (The Pile)

Max Activating Token Index: 613

Text #8

Max Range: 7.4421. Min Range: -7.4421

Max Act: 7.0393. Min Act: -0.0000

Data Index: 1890157 (The Pile)

Max Activating Token Index: 739

Text #9

Max Range: 7.4421. Min Range: -7.4421

Max Act: 6.0416. Min Act: -0.0000

Data Index: 1195381 (The Pile)

Max Activating Token Index: 539

Text #10

Max Range: 7.4421. Min Range: -7.4421

Max Act: 6.3483. Min Act: -0.0000

Data Index: 1670497 (The Pile)

Max Activating Token Index: 621

Text #11

Max Range: 7.4421. Min Range: -7.4421

Max Act: 6.5168. Min Act: -0.0000

Data Index: 1949182 (The Pile)

Max Activating Token Index: 758

Text #12

Max Range: 7.4421. Min Range: -7.4421

Max Act: 6.6529. Min Act: -0.0000

Data Index: 90688 (The Pile)

Max Activating Token Index: 363

Text #13

Max Range: 7.4421. Min Range: -7.4421

Max Act: 5.8728. Min Act: -0.0000

Data Index: 192179 (The Pile)

Max Activating Token Index: 601

Text #14

Max Range: 7.4421. Min Range: -7.4421

Max Act: 6.2123. Min Act: -0.0000

Data Index: 1640712 (The Pile)

Max Activating Token Index: 109

Text #15

Max Range: 7.4421. Min Range: -7.4421

Max Act: 5.6527. Min Act: -0.0000

Data Index: 1251053 (The Pile)

Max Activating Token Index: 622

Text #16

Max Range: 7.4421. Min Range: -7.4421

Max Act: 6.0117. Min Act: -0.0000

Data Index: 1123679 (The Pile)

Max Activating Token Index: 629

Text #17

Max Range: 7.4421. Min Range: -7.4421

Max Act: 6.1667. Min Act: -0.0000

Data Index: 1564685 (The Pile)

Max Activating Token Index: 485

Text #18

Max Range: 7.4421. Min Range: -7.4421

Max Act: 5.8958. Min Act: -0.0000

Data Index: 353989 (The Pile)

Max Activating Token Index: 454

Text #19

Max Range: 7.4421. Min Range: -7.4421

Max Act: 5.5959. Min Act: -0.0000

Data Index: 493732 (The Pile)

Max Activating Token Index: 407