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

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

Neuron 82 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.5365. Min Act: -0.0001

Data Index: 866853 (C4 (Web Text))

Max Activating Token Index: 663

Text #1

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.5147. Min Act: -0.0001

Data Index: 700201 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.5883. Min Act: -0.0001

Data Index: 304011 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.5546. Min Act: -0.0001

Data Index: 310683 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4883. Min Act: -0.0001

Data Index: 495775 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.5400. Min Act: -0.0001

Data Index: 1284111 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4887. Min Act: -0.0001

Data Index: 1277654 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4898. Min Act: -0.0001

Data Index: 699856 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.5038. Min Act: -0.0001

Data Index: 1267228 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.5629. Min Act: -0.0000

Data Index: 946696 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4297. Min Act: -0.0001

Data Index: 843043 (C4 (Web Text))

Max Activating Token Index: 909

Text #11

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4803. Min Act: -0.0001

Data Index: 1066106 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4955. Min Act: -0.0001

Data Index: 488159 (C4 (Web Text))

Max Activating Token Index: 496

Text #13

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4134. Min Act: -0.0001

Data Index: 592772 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4284. Min Act: -0.0001

Data Index: 625803 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.3699. Min Act: -0.0001

Data Index: 549910 (C4 (Web Text))

Max Activating Token Index: 248

Text #16

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4211. Min Act: -0.0001

Data Index: 768471 (C4 (Web Text))

Max Activating Token Index: 378

Text #17

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4479. Min Act: -0.0001

Data Index: 758693 (C4 (Web Text))

Max Activating Token Index: 197

Text #18

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4985. Min Act: -0.0001

Data Index: 201301 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 0.5883. Min Range: -0.5883

Max Act: 0.4820. Min Act: -0.0001

Data Index: 130442 (C4 (Web Text))

Max Activating Token Index: 90