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

Dataset: The Pile

Neuron 113 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1084. Min Act: -0.0001

Data Index: 721657 (The Pile)

Max Activating Token Index: 216

Text #1

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1087. Min Act: -0.0001

Data Index: 1365153 (The Pile)

Max Activating Token Index: 172

Text #2

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1010. Min Act: -0.0001

Data Index: 295573 (The Pile)

Max Activating Token Index: 383

Text #3

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1030. Min Act: -0.0001

Data Index: 252699 (The Pile)

Max Activating Token Index: 200

Text #4

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0982. Min Act: -0.0001

Data Index: 1060366 (The Pile)

Max Activating Token Index: 644

Text #5

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1023. Min Act: -0.0001

Data Index: 278858 (The Pile)

Max Activating Token Index: 349

Text #6

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0978. Min Act: -0.0001

Data Index: 738793 (The Pile)

Max Activating Token Index: 1006

Text #7

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1109. Min Act: -0.0001

Data Index: 1502008 (The Pile)

Max Activating Token Index: 1000

Text #8

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0977. Min Act: -0.0001

Data Index: 451113 (The Pile)

Max Activating Token Index: 348

Text #9

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0942. Min Act: -0.0001

Data Index: 1608061 (The Pile)

Max Activating Token Index: 793

Text #10

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0894. Min Act: -0.0001

Data Index: 1544365 (The Pile)

Max Activating Token Index: 863

Text #11

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0917. Min Act: -0.0001

Data Index: 410904 (The Pile)

Max Activating Token Index: 275

Text #12

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0893. Min Act: -0.0001

Data Index: 273482 (The Pile)

Max Activating Token Index: 374

Text #13

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1090. Min Act: -0.0001

Data Index: 540967 (The Pile)

Max Activating Token Index: 208

Text #14

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0986. Min Act: -0.0001

Data Index: 817780 (The Pile)

Max Activating Token Index: 911

Text #15

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0949. Min Act: -0.0001

Data Index: 878203 (The Pile)

Max Activating Token Index: 155

Text #16

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0951. Min Act: -0.0001

Data Index: 588390 (The Pile)

Max Activating Token Index: 3

Text #17

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0865. Min Act: -0.0001

Data Index: 1746826 (The Pile)

Max Activating Token Index: 354

Text #18

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0943. Min Act: -0.0001

Data Index: 842495 (The Pile)

Max Activating Token Index: 13

Text #19

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0864. Min Act: -0.0001

Data Index: 572235 (The Pile)

Max Activating Token Index: 699