Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1145 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.6736. Min Act: -0.0001

Data Index: 366234 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.5248. Min Act: -0.0000

Data Index: 751742 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.4608. Min Act: -0.0001

Data Index: 1315927 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.4828. Min Act: -0.0000

Data Index: 911293 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.5154. Min Act: -0.0001

Data Index: 1197264 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.5276. Min Act: -0.0001

Data Index: 1347886 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.5026. Min Act: -0.0000

Data Index: 1523347 (Python Code)

Max Activating Token Index: 136

Text #7

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.4998. Min Act: -0.0000

Data Index: 1304886 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.4981. Min Act: -0.0001

Data Index: 996611 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.3677. Min Act: -0.0000

Data Index: 851954 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.3889. Min Act: -0.0000

Data Index: 158985 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.4866. Min Act: -0.0000

Data Index: 692800 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.4468. Min Act: -0.0000

Data Index: 1368544 (Python Code)

Max Activating Token Index: 191

Text #13

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.4123. Min Act: -0.0001

Data Index: 995222 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.3948. Min Act: -0.0001

Data Index: 158017 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.4921. Min Act: -0.0001

Data Index: 8844 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.4120. Min Act: -0.0000

Data Index: 1370299 (Python Code)

Max Activating Token Index: 20

Text #17

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.3462. Min Act: -0.0000

Data Index: 1349147 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.4333. Min Act: -0.0000

Data Index: 1578637 (Python Code)

Max Activating Token Index: 731

Text #19

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.4225. Min Act: -0.0001

Data Index: 1556190 (Python Code)

Max Activating Token Index: 131