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

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

Neuron 1249 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0495. Min Range: -1.0495

Max Act: 1.0495. Min Act: -0.0000

Data Index: 827 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 1.0495. Min Range: -1.0495

Max Act: 1.0155. Min Act: -0.0000

Data Index: 828912 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.9854. Min Act: -0.0000

Data Index: 964090 (C4 (Web Text))

Max Activating Token Index: 762

Text #3

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.9463. Min Act: -0.0000

Data Index: 115171 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.9448. Min Act: -0.0000

Data Index: 258881 (C4 (Web Text))

Max Activating Token Index: 405

Text #5

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.8862. Min Act: -0.0000

Data Index: 1185197 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.8761. Min Act: -0.0000

Data Index: 974477 (C4 (Web Text))

Max Activating Token Index: 19

Text #7

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.8669. Min Act: -0.0000

Data Index: 400595 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.8270. Min Act: -0.0000

Data Index: 1251918 (C4 (Web Text))

Max Activating Token Index: 695

Text #9

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.8547. Min Act: -0.0000

Data Index: 337757 (C4 (Web Text))

Max Activating Token Index: 684

Text #10

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.8109. Min Act: -0.0000

Data Index: 1246344 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.8312. Min Act: -0.0000

Data Index: 680890 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.7640. Min Act: -0.0000

Data Index: 673158 (C4 (Web Text))

Max Activating Token Index: 759

Text #13

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.8414. Min Act: -0.0000

Data Index: 1088991 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.8061. Min Act: -0.0000

Data Index: 99974 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.7959. Min Act: -0.0000

Data Index: 863502 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.7876. Min Act: -0.0000

Data Index: 5249 (C4 (Web Text))

Max Activating Token Index: 941

Text #17

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.7369. Min Act: -0.0000

Data Index: 466789 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.7492. Min Act: -0.0000

Data Index: 805604 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 1.0495. Min Range: -1.0495

Max Act: 0.7840. Min Act: -0.0000

Data Index: 464902 (C4 (Web Text))

Max Activating Token Index: 680