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

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

Neuron 4570 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.8631. Min Act: -0.0000

Data Index: 19206 (C4 (Web Text))

Max Activating Token Index: 822

Text #1

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.9055. Min Act: -0.0000

Data Index: 432518 (C4 (Web Text))

Max Activating Token Index: 855

Text #2

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.8538. Min Act: -0.0000

Data Index: 798029 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.8161. Min Act: -0.0000

Data Index: 1306533 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.8073. Min Act: 0.0001

Data Index: 942721 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.7911. Min Act: -0.0000

Data Index: 976566 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.7844. Min Act: -0.0000

Data Index: 268068 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.7330. Min Act: -0.0000

Data Index: 945192 (C4 (Web Text))

Max Activating Token Index: 876

Text #8

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.7296. Min Act: -0.0000

Data Index: 54730 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.7970. Min Act: -0.0000

Data Index: 380955 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.7165. Min Act: -0.0000

Data Index: 1358004 (C4 (Web Text))

Max Activating Token Index: 846

Text #11

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.7354. Min Act: -0.0000

Data Index: 548560 (C4 (Web Text))

Max Activating Token Index: 459

Text #12

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.6905. Min Act: -0.0000

Data Index: 382282 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.6823. Min Act: 0.0001

Data Index: 247539 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.7435. Min Act: -0.0000

Data Index: 937543 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.6750. Min Act: -0.0000

Data Index: 902386 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.6875. Min Act: -0.0000

Data Index: 1357822 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.6782. Min Act: 0.0001

Data Index: 150552 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.6797. Min Act: -0.0000

Data Index: 683735 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.6725. Min Act: -0.0000

Data Index: 671942 (C4 (Web Text))

Max Activating Token Index: 275