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

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

Neuron 2693 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: 3.5594. Min Range: -3.5594

Max Act: 3.5594. Min Act: -0.0001

Data Index: 153631 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 3.5594. Min Range: -3.5594

Max Act: 3.4074. Min Act: -0.0001

Data Index: 1055227 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 3.5594. Min Range: -3.5594

Max Act: 3.4841. Min Act: -0.0001

Data Index: 143572 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 3.5594. Min Range: -3.5594

Max Act: 3.1279. Min Act: -0.0001

Data Index: 766959 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 3.5594. Min Range: -3.5594

Max Act: 3.1026. Min Act: -0.0001

Data Index: 692904 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 3.5594. Min Range: -3.5594

Max Act: 3.1795. Min Act: -0.0001

Data Index: 656044 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 3.5594. Min Range: -3.5594

Max Act: 2.9931. Min Act: -0.0001

Data Index: 502640 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 3.5594. Min Range: -3.5594

Max Act: 3.1135. Min Act: -0.0001

Data Index: 1016348 (C4 (Web Text))

Max Activating Token Index: 824

Text #8

Max Range: 3.5594. Min Range: -3.5594

Max Act: 3.0931. Min Act: -0.0001

Data Index: 409848 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 3.5594. Min Range: -3.5594

Max Act: 3.0895. Min Act: -0.0001

Data Index: 823143 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 3.5594. Min Range: -3.5594

Max Act: 2.8969. Min Act: -0.0001

Data Index: 556902 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 3.5594. Min Range: -3.5594

Max Act: 2.7280. Min Act: -0.0001

Data Index: 815388 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 3.5594. Min Range: -3.5594

Max Act: 2.9838. Min Act: -0.0001

Data Index: 463644 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 3.5594. Min Range: -3.5594

Max Act: 2.9909. Min Act: -0.0000

Data Index: 61463 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 3.5594. Min Range: -3.5594

Max Act: 2.8465. Min Act: -0.0001

Data Index: 58460 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 3.5594. Min Range: -3.5594

Max Act: 2.9686. Min Act: -0.0001

Data Index: 1194384 (C4 (Web Text))

Max Activating Token Index: 904

Text #16

Max Range: 3.5594. Min Range: -3.5594

Max Act: 2.7854. Min Act: -0.0001

Data Index: 965978 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 3.5594. Min Range: -3.5594

Max Act: 2.8923. Min Act: -0.0001

Data Index: 881969 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 3.5594. Min Range: -3.5594

Max Act: 2.8797. Min Act: -0.0001

Data Index: 885969 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 3.5594. Min Range: -3.5594

Max Act: 2.9508. Min Act: -0.0001

Data Index: 32329 (C4 (Web Text))

Max Activating Token Index: 724