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

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

Neuron 1711 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: 0.7729. Min Range: -0.7729

Max Act: 0.7729. Min Act: -0.0001

Data Index: 829041 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.7398. Min Act: -0.0001

Data Index: 115553 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.6609. Min Act: -0.0001

Data Index: 395094 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.7140. Min Act: -0.0001

Data Index: 466784 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.6816. Min Act: -0.0001

Data Index: 1232577 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.6904. Min Act: -0.0001

Data Index: 288321 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.6262. Min Act: -0.0001

Data Index: 938595 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.6769. Min Act: -0.0001

Data Index: 1014317 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.6654. Min Act: -0.0001

Data Index: 709768 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.6391. Min Act: -0.0001

Data Index: 215305 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.6205. Min Act: -0.0001

Data Index: 1564572 (Python Code)

Max Activating Token Index: 796

Text #11

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.6568. Min Act: -0.0001

Data Index: 1247548 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.6496. Min Act: -0.0001

Data Index: 1298801 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.7243. Min Act: -0.0001

Data Index: 473031 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.6514. Min Act: -0.0001

Data Index: 767523 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.6381. Min Act: -0.0001

Data Index: 427634 (C4 (Web Text))

Max Activating Token Index: 456

Text #16

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.6465. Min Act: -0.0001

Data Index: 1136398 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.5900. Min Act: -0.0001

Data Index: 582161 (C4 (Web Text))

Max Activating Token Index: 651

Text #18

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.6685. Min Act: -0.0001

Data Index: 1244268 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 0.7729. Min Range: -0.7729

Max Act: 0.6257. Min Act: -0.0001

Data Index: 450266 (C4 (Web Text))

Max Activating Token Index: 693