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

Dataset: The Pile

Neuron 2716 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.4594. Min Act: -0.0000

Data Index: 1149971 (The Pile)

Max Activating Token Index: 802

Text #1

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3965. Min Act: -0.0000

Data Index: 1048393 (The Pile)

Max Activating Token Index: 948

Text #2

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3828. Min Act: -0.0000

Data Index: 653901 (The Pile)

Max Activating Token Index: 931

Text #3

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.4007. Min Act: -0.0000

Data Index: 755703 (The Pile)

Max Activating Token Index: 908

Text #4

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.4003. Min Act: -0.0000

Data Index: 19271 (The Pile)

Max Activating Token Index: 824

Text #5

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3965. Min Act: -0.0000

Data Index: 87336 (The Pile)

Max Activating Token Index: 937

Text #6

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3906. Min Act: -0.0000

Data Index: 1996053 (The Pile)

Max Activating Token Index: 876

Text #7

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.4343. Min Act: -0.0000

Data Index: 1385689 (The Pile)

Max Activating Token Index: 692

Text #8

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3550. Min Act: -0.0000

Data Index: 1012432 (The Pile)

Max Activating Token Index: 794

Text #9

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3478. Min Act: -0.0000

Data Index: 1050267 (The Pile)

Max Activating Token Index: 980

Text #10

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3339. Min Act: -0.0000

Data Index: 416248 (The Pile)

Max Activating Token Index: 993

Text #11

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3694. Min Act: -0.0000

Data Index: 384676 (The Pile)

Max Activating Token Index: 843

Text #12

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3584. Min Act: -0.0000

Data Index: 1253645 (The Pile)

Max Activating Token Index: 929

Text #13

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3477. Min Act: -0.0000

Data Index: 321134 (The Pile)

Max Activating Token Index: 915

Text #14

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3736. Min Act: -0.0000

Data Index: 1540648 (The Pile)

Max Activating Token Index: 879

Text #15

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3443. Min Act: -0.0000

Data Index: 1041238 (The Pile)

Max Activating Token Index: 1011

Text #16

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3510. Min Act: -0.0000

Data Index: 1900247 (The Pile)

Max Activating Token Index: 893

Text #17

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3781. Min Act: -0.0000

Data Index: 23960 (The Pile)

Max Activating Token Index: 993

Text #18

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3733. Min Act: -0.0000

Data Index: 281884 (The Pile)

Max Activating Token Index: 867

Text #19

Max Range: 0.4594. Min Range: -0.4594

Max Act: 0.3579. Min Act: -0.0000

Data Index: 879964 (The Pile)

Max Activating Token Index: 725