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

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

Neuron 879 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: 0.1000. Min Range: -0.1000

Max Act: 0.1000. Min Act: -0.0000

Data Index: 1278359 (C4 (Web Text))

Max Activating Token Index: 862

Text #1

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0693. Min Act: -0.0001

Data Index: 305351 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0743. Min Act: -0.0000

Data Index: 440596 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0643. Min Act: -0.0000

Data Index: 858385 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0565. Min Act: -0.0001

Data Index: 290009 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0601. Min Act: -0.0001

Data Index: 1488744 (Python Code)

Max Activating Token Index: 998

Text #6

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0643. Min Act: -0.0001

Data Index: 1382139 (Python Code)

Max Activating Token Index: 637

Text #7

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0578. Min Act: -0.0001

Data Index: 694300 (C4 (Web Text))

Max Activating Token Index: 808

Text #8

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0550. Min Act: -0.0000

Data Index: 547900 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0580. Min Act: -0.0000

Data Index: 181696 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0567. Min Act: -0.0000

Data Index: 1195083 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0433. Min Act: -0.0000

Data Index: 1101459 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0529. Min Act: -0.0001

Data Index: 1516902 (Python Code)

Max Activating Token Index: 944

Text #13

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0521. Min Act: -0.0000

Data Index: 228961 (C4 (Web Text))

Max Activating Token Index: 998

Text #14

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0491. Min Act: -0.0000

Data Index: 1136159 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0493. Min Act: -0.0000

Data Index: 1403104 (Python Code)

Max Activating Token Index: 212

Text #16

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0525. Min Act: -0.0000

Data Index: 857214 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0509. Min Act: -0.0000

Data Index: 1493132 (Python Code)

Max Activating Token Index: 955

Text #18

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0498. Min Act: -0.0001

Data Index: 863376 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0562. Min Act: -0.0001

Data Index: 782671 (C4 (Web Text))

Max Activating Token Index: 602