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

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

Neuron 740 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1377. Min Act: -0.0000

Data Index: 651578 (C4 (Web Text))

Max Activating Token Index: 344

Text #1

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1351. Min Act: -0.0000

Data Index: 961589 (C4 (Web Text))

Max Activating Token Index: 690

Text #2

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1414. Min Act: -0.0000

Data Index: 296917 (C4 (Web Text))

Max Activating Token Index: 939

Text #3

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1344. Min Act: -0.0000

Data Index: 1325497 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1212. Min Act: -0.0000

Data Index: 1125570 (C4 (Web Text))

Max Activating Token Index: 390

Text #5

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1237. Min Act: -0.0000

Data Index: 1051275 (C4 (Web Text))

Max Activating Token Index: 1003

Text #6

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1199. Min Act: -0.0000

Data Index: 305576 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1231. Min Act: -0.0000

Data Index: 1231215 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1077. Min Act: -0.0000

Data Index: 1635093 (Python Code)

Max Activating Token Index: 902

Text #9

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1080. Min Act: -0.0000

Data Index: 1236009 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1110. Min Act: -0.0000

Data Index: 822962 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0986. Min Act: -0.0000

Data Index: 52243 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1006. Min Act: -0.0000

Data Index: 873079 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1034. Min Act: -0.0000

Data Index: 1621592 (Python Code)

Max Activating Token Index: 981

Text #14

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.1019. Min Act: -0.0000

Data Index: 1535208 (Python Code)

Max Activating Token Index: 217

Text #15

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0999. Min Act: -0.0000

Data Index: 821301 (C4 (Web Text))

Max Activating Token Index: 964

Text #16

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0978. Min Act: -0.0000

Data Index: 1425443 (Python Code)

Max Activating Token Index: 459

Text #17

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0914. Min Act: -0.0000

Data Index: 1408863 (Python Code)

Max Activating Token Index: 776

Text #18

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0973. Min Act: -0.0000

Data Index: 388843 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 0.1414. Min Range: -0.1414

Max Act: 0.0938. Min Act: -0.0000

Data Index: 1320707 (C4 (Web Text))

Max Activating Token Index: 995