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

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

Neuron 5905 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: 0.6501. Min Range: -0.6501

Max Act: 0.6166. Min Act: -0.0000

Data Index: 1125306 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.5914. Min Act: -0.0000

Data Index: 131080 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.6291. Min Act: -0.0000

Data Index: 22258 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.5750. Min Act: -0.0000

Data Index: 254816 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.6501. Min Act: -0.0000

Data Index: 714532 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.5953. Min Act: -0.0000

Data Index: 89477 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.6060. Min Act: -0.0000

Data Index: 797806 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.6072. Min Act: -0.0000

Data Index: 611752 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.6223. Min Act: -0.0000

Data Index: 574871 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.5821. Min Act: -0.0000

Data Index: 1183886 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.5418. Min Act: -0.0000

Data Index: 947200 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.5218. Min Act: -0.0000

Data Index: 663987 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.5611. Min Act: -0.0000

Data Index: 860391 (C4 (Web Text))

Max Activating Token Index: 916

Text #13

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.5478. Min Act: -0.0000

Data Index: 139868 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.5333. Min Act: -0.0000

Data Index: 179538 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.5450. Min Act: -0.0000

Data Index: 1119501 (C4 (Web Text))

Max Activating Token Index: 714

Text #16

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.5091. Min Act: -0.0000

Data Index: 982855 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.5260. Min Act: -0.0000

Data Index: 182112 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.5083. Min Act: -0.0000

Data Index: 903201 (C4 (Web Text))

Max Activating Token Index: 606

Text #19

Max Range: 0.6501. Min Range: -0.6501

Max Act: 0.4980. Min Act: -0.0000

Data Index: 1012357 (C4 (Web Text))

Max Activating Token Index: 143