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

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

Neuron 3651 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1396. Min Range: -2.1396

Max Act: 2.1396. Min Act: -0.0000

Data Index: 1227792 (C4 (Web Text))

Max Activating Token Index: 510

Text #1

Max Range: 2.1396. Min Range: -2.1396

Max Act: 1.8563. Min Act: -0.0000

Data Index: 584233 (C4 (Web Text))

Max Activating Token Index: 442

Text #2

Max Range: 2.1396. Min Range: -2.1396

Max Act: 1.5547. Min Act: -0.0000

Data Index: 646824 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 2.1396. Min Range: -2.1396

Max Act: 1.3961. Min Act: -0.0000

Data Index: 572512 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 2.1396. Min Range: -2.1396

Max Act: 1.3180. Min Act: -0.0000

Data Index: 790529 (C4 (Web Text))

Max Activating Token Index: 657

Text #5

Max Range: 2.1396. Min Range: -2.1396

Max Act: 1.2437. Min Act: 0.0000

Data Index: 570963 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 2.1396. Min Range: -2.1396

Max Act: 1.2821. Min Act: -0.0000

Data Index: 366965 (C4 (Web Text))

Max Activating Token Index: 668

Text #7

Max Range: 2.1396. Min Range: -2.1396

Max Act: 0.9790. Min Act: -0.0000

Data Index: 856263 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 2.1396. Min Range: -2.1396

Max Act: 1.2713. Min Act: -0.0000

Data Index: 165812 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 2.1396. Min Range: -2.1396

Max Act: 1.0860. Min Act: -0.0000

Data Index: 1214133 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 2.1396. Min Range: -2.1396

Max Act: 1.1574. Min Act: -0.0000

Data Index: 1323825 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 2.1396. Min Range: -2.1396

Max Act: 1.1066. Min Act: -0.0000

Data Index: 915905 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 2.1396. Min Range: -2.1396

Max Act: 1.0401. Min Act: -0.0000

Data Index: 1218734 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 2.1396. Min Range: -2.1396

Max Act: 0.9014. Min Act: -0.0000

Data Index: 1386743 (Python Code)

Max Activating Token Index: 755

Text #14

Max Range: 2.1396. Min Range: -2.1396

Max Act: 1.0216. Min Act: -0.0000

Data Index: 667844 (C4 (Web Text))

Max Activating Token Index: 400

Text #15

Max Range: 2.1396. Min Range: -2.1396

Max Act: 0.9719. Min Act: -0.0000

Data Index: 1199499 (C4 (Web Text))

Max Activating Token Index: 531

Text #16

Max Range: 2.1396. Min Range: -2.1396

Max Act: 0.9464. Min Act: -0.0000

Data Index: 448801 (C4 (Web Text))

Max Activating Token Index: 622

Text #17

Max Range: 2.1396. Min Range: -2.1396

Max Act: 0.9297. Min Act: -0.0000

Data Index: 1627686 (Python Code)

Max Activating Token Index: 992

Text #18

Max Range: 2.1396. Min Range: -2.1396

Max Act: 0.9104. Min Act: -0.0000

Data Index: 226426 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 2.1396. Min Range: -2.1396

Max Act: 0.9996. Min Act: -0.0000

Data Index: 1327884 (C4 (Web Text))

Max Activating Token Index: 85