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

Dataset: The Pile

Neuron 4488 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: 0.4773. Min Range: -0.4773

Max Act: 0.4773. Min Act: -0.0000

Data Index: 1042141 (The Pile)

Max Activating Token Index: 383

Text #1

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.3968. Min Act: -0.0000

Data Index: 1480544 (The Pile)

Max Activating Token Index: 675

Text #2

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.4073. Min Act: -0.0000

Data Index: 21610 (The Pile)

Max Activating Token Index: 629

Text #3

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.3900. Min Act: -0.0000

Data Index: 10647 (The Pile)

Max Activating Token Index: 966

Text #4

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.3929. Min Act: -0.0000

Data Index: 509345 (The Pile)

Max Activating Token Index: 500

Text #5

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.3851. Min Act: -0.0000

Data Index: 1612954 (The Pile)

Max Activating Token Index: 626

Text #6

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.3753. Min Act: -0.0000

Data Index: 482249 (The Pile)

Max Activating Token Index: 748

Text #7

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.3704. Min Act: -0.0000

Data Index: 101303 (The Pile)

Max Activating Token Index: 743

Text #8

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.3958. Min Act: -0.0000

Data Index: 161607 (The Pile)

Max Activating Token Index: 581

Text #9

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.3887. Min Act: -0.0000

Data Index: 1953093 (The Pile)

Max Activating Token Index: 646

Text #10

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.3911. Min Act: -0.0000

Data Index: 1638096 (The Pile)

Max Activating Token Index: 606

Text #11

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.3738. Min Act: -0.0000

Data Index: 973458 (The Pile)

Max Activating Token Index: 606

Text #12

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.3429. Min Act: -0.0000

Data Index: 904903 (The Pile)

Max Activating Token Index: 878

Text #13

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.3762. Min Act: -0.0000

Data Index: 1391796 (The Pile)

Max Activating Token Index: 643

Text #14

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.3932. Min Act: -0.0000

Data Index: 1616235 (The Pile)

Max Activating Token Index: 564

Text #15

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.3921. Min Act: -0.0000

Data Index: 660815 (The Pile)

Max Activating Token Index: 735

Text #16

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.3413. Min Act: -0.0000

Data Index: 1327325 (The Pile)

Max Activating Token Index: 595

Text #17

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.3766. Min Act: -0.0000

Data Index: 975836 (The Pile)

Max Activating Token Index: 665

Text #18

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.3743. Min Act: -0.0000

Data Index: 1290325 (The Pile)

Max Activating Token Index: 613

Text #19

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.3303. Min Act: -0.0000

Data Index: 1565016 (The Pile)

Max Activating Token Index: 836