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

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

Neuron 3027 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0746. Min Act: -0.0002

Data Index: 1277642 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0750. Min Act: -0.0002

Data Index: 291157 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0599. Min Act: -0.0002

Data Index: 47969 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0574. Min Act: -0.0002

Data Index: 978820 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0561. Min Act: -0.0002

Data Index: 866755 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0586. Min Act: -0.0002

Data Index: 1168925 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0539. Min Act: -0.0002

Data Index: 1344269 (C4 (Web Text))

Max Activating Token Index: 351

Text #7

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1226001 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0516. Min Act: -0.0002

Data Index: 994837 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0520. Min Act: -0.0002

Data Index: 862658 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0536. Min Act: -0.0002

Data Index: 1179200 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0529. Min Act: -0.0002

Data Index: 428333 (C4 (Web Text))

Max Activating Token Index: 641

Text #12

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0516. Min Act: -0.0002

Data Index: 601356 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0472. Min Act: -0.0002

Data Index: 448349 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0506. Min Act: -0.0002

Data Index: 123822 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0495. Min Act: -0.0002

Data Index: 693000 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0497. Min Act: -0.0002

Data Index: 764984 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0492. Min Act: -0.0002

Data Index: 1053766 (C4 (Web Text))

Max Activating Token Index: 473

Text #18

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0489. Min Act: -0.0002

Data Index: 126715 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0501. Min Act: -0.0002

Data Index: 410003 (C4 (Web Text))

Max Activating Token Index: 724