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

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

Neuron 1082 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.7559. Min Act: -0.0000

Data Index: 1561493 (Python Code)

Max Activating Token Index: 206

Text #1

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.7723. Min Act: -0.0000

Data Index: 1103047 (C4 (Web Text))

Max Activating Token Index: 877

Text #2

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.8075. Min Act: -0.0000

Data Index: 1544913 (Python Code)

Max Activating Token Index: 393

Text #3

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.7922. Min Act: -0.0000

Data Index: 1563018 (Python Code)

Max Activating Token Index: 859

Text #4

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.7987. Min Act: -0.0000

Data Index: 1600703 (Python Code)

Max Activating Token Index: 913

Text #5

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6762. Min Act: -0.0000

Data Index: 889547 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6300. Min Act: -0.0000

Data Index: 1535806 (Python Code)

Max Activating Token Index: 249

Text #7

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.7124. Min Act: -0.0000

Data Index: 1486986 (Python Code)

Max Activating Token Index: 534

Text #8

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.5844. Min Act: -0.0000

Data Index: 1543057 (Python Code)

Max Activating Token Index: 766

Text #9

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6703. Min Act: 0.0000

Data Index: 1590300 (Python Code)

Max Activating Token Index: 410

Text #10

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6521. Min Act: -0.0000

Data Index: 1536302 (Python Code)

Max Activating Token Index: 509

Text #11

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6322. Min Act: -0.0000

Data Index: 1405047 (Python Code)

Max Activating Token Index: 233

Text #12

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6420. Min Act: -0.0000

Data Index: 1546106 (Python Code)

Max Activating Token Index: 532

Text #13

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6753. Min Act: -0.0000

Data Index: 644545 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6141. Min Act: -0.0000

Data Index: 1425644 (Python Code)

Max Activating Token Index: 706

Text #15

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6476. Min Act: -0.0000

Data Index: 1504202 (Python Code)

Max Activating Token Index: 857

Text #16

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6412. Min Act: -0.0000

Data Index: 1533154 (Python Code)

Max Activating Token Index: 254

Text #17

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6222. Min Act: -0.0000

Data Index: 1464159 (Python Code)

Max Activating Token Index: 556

Text #18

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6324. Min Act: -0.0000

Data Index: 1417069 (Python Code)

Max Activating Token Index: 690

Text #19

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6388. Min Act: -0.0000

Data Index: 1562726 (Python Code)

Max Activating Token Index: 987