Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2154 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.9088. Min Act: -0.0000

Data Index: 855959 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.8943. Min Act: -0.0000

Data Index: 475466 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.8549. Min Act: -0.0000

Data Index: 124473 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.8125. Min Act: -0.0000

Data Index: 871963 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.8597. Min Act: -0.0000

Data Index: 1148515 (C4 (Web Text))

Max Activating Token Index: 577

Text #5

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.8455. Min Act: -0.0000

Data Index: 727214 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.8057. Min Act: -0.0000

Data Index: 1252906 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.7494. Min Act: -0.0000

Data Index: 1335569 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.8061. Min Act: -0.0000

Data Index: 922566 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.7764. Min Act: -0.0000

Data Index: 1303404 (C4 (Web Text))

Max Activating Token Index: 431

Text #10

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.7983. Min Act: -0.0000

Data Index: 409857 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.7942. Min Act: -0.0000

Data Index: 459805 (C4 (Web Text))

Max Activating Token Index: 462

Text #12

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.7417. Min Act: -0.0000

Data Index: 1028608 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.7710. Min Act: -0.0000

Data Index: 552148 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.7181. Min Act: -0.0000

Data Index: 419364 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.7220. Min Act: -0.0000

Data Index: 107978 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.7138. Min Act: -0.0000

Data Index: 650534 (C4 (Web Text))

Max Activating Token Index: 997

Text #17

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.6940. Min Act: -0.0000

Data Index: 580541 (C4 (Web Text))

Max Activating Token Index: 362

Text #18

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.7116. Min Act: -0.0000

Data Index: 867748 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 0.9088. Min Range: -0.9088

Max Act: 0.7077. Min Act: -0.0000

Data Index: 1092962 (C4 (Web Text))

Max Activating Token Index: 493