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

Dataset: The Pile

Neuron 1990 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: 0.7622. Min Range: -0.7622

Max Act: 0.7622. Min Act: -0.0000

Data Index: 838784 (The Pile)

Max Activating Token Index: 657

Text #1

Max Range: 0.7622. Min Range: -0.7622

Max Act: 0.6582. Min Act: -0.0000

Data Index: 1844358 (The Pile)

Max Activating Token Index: 959

Text #2

Max Range: 0.7622. Min Range: -0.7622

Max Act: 0.6207. Min Act: -0.0000

Data Index: 1989099 (The Pile)

Max Activating Token Index: 441

Text #3

Max Range: 0.7622. Min Range: -0.7622

Max Act: 0.5555. Min Act: -0.0000

Data Index: 415319 (The Pile)

Max Activating Token Index: 761

Text #4

Max Range: 0.7622. Min Range: -0.7622

Max Act: 0.6424. Min Act: -0.0000

Data Index: 1041150 (The Pile)

Max Activating Token Index: 640

Text #5

Max Range: 0.7622. Min Range: -0.7622

Max Act: 0.5480. Min Act: -0.0000

Data Index: 137611 (The Pile)

Max Activating Token Index: 755

Text #6

Max Range: 0.7622. Min Range: -0.7622

Max Act: 0.4729. Min Act: -0.0000

Data Index: 176467 (The Pile)

Max Activating Token Index: 102

Text #7

Max Range: 0.7622. Min Range: -0.7622

Max Act: 0.5049. Min Act: -0.0000

Data Index: 1557753 (The Pile)

Max Activating Token Index: 506

Text #8

Max Range: 0.7622. Min Range: -0.7622

Max Act: 0.4755. Min Act: -0.0000

Data Index: 255097 (The Pile)

Max Activating Token Index: 769

Text #9

Max Range: 0.7622. Min Range: -0.7622

Max Act: 0.4561. Min Act: -0.0000

Data Index: 963577 (The Pile)

Max Activating Token Index: 648

Text #10

Max Range: 0.7622. Min Range: -0.7622

Max Act: 0.4821. Min Act: -0.0000

Data Index: 1509561 (The Pile)

Max Activating Token Index: 656

Text #11

Max Range: 0.7622. Min Range: -0.7622

Max Act: 0.4797. Min Act: -0.0000

Data Index: 1350286 (The Pile)

Max Activating Token Index: 991

Text #12

Max Range: 0.7622. Min Range: -0.7622

Max Act: 0.4851. Min Act: -0.0000

Data Index: 65462 (The Pile)

Max Activating Token Index: 760

Text #13

Max Range: 0.7622. Min Range: -0.7622

Max Act: 0.4722. Min Act: -0.0000

Data Index: 1611611 (The Pile)

Max Activating Token Index: 435

Text #14

Max Range: 0.7622. Min Range: -0.7622

Max Act: 0.4629. Min Act: -0.0000

Data Index: 688677 (The Pile)

Max Activating Token Index: 204

Text #15

Max Range: 0.7622. Min Range: -0.7622

Max Act: 0.4849. Min Act: -0.0000

Data Index: 1987657 (The Pile)

Max Activating Token Index: 879

Text #16

Max Range: 0.7622. Min Range: -0.7622

Max Act: 0.4624. Min Act: -0.0000

Data Index: 1655773 (The Pile)

Max Activating Token Index: 209

Text #17

Max Range: 0.7622. Min Range: -0.7622

Max Act: 0.4460. Min Act: -0.0000

Data Index: 1952236 (The Pile)

Max Activating Token Index: 251

Text #18

Max Range: 0.7622. Min Range: -0.7622

Max Act: 0.4400. Min Act: -0.0000

Data Index: 1504076 (The Pile)

Max Activating Token Index: 583

Text #19

Max Range: 0.7622. Min Range: -0.7622

Max Act: 0.5145. Min Act: -0.0000

Data Index: 700910 (The Pile)

Max Activating Token Index: 778