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

Dataset: The Pile

Neuron 3166 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: 0.6339. Min Range: -0.6339

Max Act: 0.6339. Min Act: 0.0000

Data Index: 465709 (The Pile)

Max Activating Token Index: 520

Text #1

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.4924. Min Act: 0.0001

Data Index: 1488423 (The Pile)

Max Activating Token Index: 997

Text #2

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.4608. Min Act: -0.0000

Data Index: 23714 (The Pile)

Max Activating Token Index: 702

Text #3

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.4509. Min Act: 0.0001

Data Index: 1983449 (The Pile)

Max Activating Token Index: 490

Text #4

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.4067. Min Act: 0.0000

Data Index: 499436 (The Pile)

Max Activating Token Index: 651

Text #5

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.4020. Min Act: -0.0000

Data Index: 1551537 (The Pile)

Max Activating Token Index: 93

Text #6

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.3909. Min Act: 0.0000

Data Index: 664531 (The Pile)

Max Activating Token Index: 983

Text #7

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.3902. Min Act: -0.0000

Data Index: 1668015 (The Pile)

Max Activating Token Index: 522

Text #8

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.4079. Min Act: -0.0000

Data Index: 872022 (The Pile)

Max Activating Token Index: 643

Text #9

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.3956. Min Act: 0.0000

Data Index: 1179104 (The Pile)

Max Activating Token Index: 223

Text #10

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.3798. Min Act: -0.0000

Data Index: 1502452 (The Pile)

Max Activating Token Index: 29

Text #11

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.3592. Min Act: 0.0000

Data Index: 1514575 (The Pile)

Max Activating Token Index: 610

Text #12

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.3793. Min Act: -0.0000

Data Index: 1325102 (The Pile)

Max Activating Token Index: 294

Text #13

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.3565. Min Act: -0.0000

Data Index: 1800544 (The Pile)

Max Activating Token Index: 638

Text #14

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.3666. Min Act: -0.0000

Data Index: 1663661 (The Pile)

Max Activating Token Index: 195

Text #15

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.3557. Min Act: 0.0001

Data Index: 505862 (The Pile)

Max Activating Token Index: 885

Text #16

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.3697. Min Act: 0.0000

Data Index: 1276856 (The Pile)

Max Activating Token Index: 293

Text #17

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.3522. Min Act: 0.0000

Data Index: 580165 (The Pile)

Max Activating Token Index: 629

Text #18

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.3540. Min Act: -0.0000

Data Index: 261525 (The Pile)

Max Activating Token Index: 739

Text #19

Max Range: 0.6339. Min Range: -0.6339

Max Act: 0.3446. Min Act: 0.0000

Data Index: 1960232 (The Pile)

Max Activating Token Index: 679