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

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

Neuron 2640 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: 0.0889. Min Range: -0.0889

Max Act: 0.0889. Min Act: -0.0000

Data Index: 1455943 (Python Code)

Max Activating Token Index: 326

Text #1

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0758. Min Act: -0.0000

Data Index: 831824 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0739. Min Act: -0.0001

Data Index: 791389 (C4 (Web Text))

Max Activating Token Index: 217

Text #3

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0606. Min Act: -0.0000

Data Index: 262772 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0540. Min Act: -0.0000

Data Index: 976102 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0600. Min Act: -0.0000

Data Index: 1583318 (Python Code)

Max Activating Token Index: 257

Text #6

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0549. Min Act: -0.0000

Data Index: 1457411 (Python Code)

Max Activating Token Index: 921

Text #7

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0498. Min Act: -0.0000

Data Index: 784386 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0528. Min Act: -0.0000

Data Index: 1470857 (Python Code)

Max Activating Token Index: 671

Text #9

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0563. Min Act: -0.0001

Data Index: 1096323 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0535. Min Act: -0.0001

Data Index: 1297509 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0514. Min Act: -0.0000

Data Index: 1543242 (Python Code)

Max Activating Token Index: 531

Text #12

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0511. Min Act: -0.0000

Data Index: 1462174 (Python Code)

Max Activating Token Index: 989

Text #13

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0443. Min Act: -0.0000

Data Index: 604818 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0546. Min Act: -0.0000

Data Index: 582325 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0529. Min Act: -0.0000

Data Index: 632219 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0454. Min Act: -0.0000

Data Index: 1411412 (Python Code)

Max Activating Token Index: 983

Text #17

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0553. Min Act: -0.0000

Data Index: 800169 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0480. Min Act: -0.0000

Data Index: 1440746 (Python Code)

Max Activating Token Index: 155

Text #19

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0496. Min Act: -0.0000

Data Index: 1648757 (Python Code)

Max Activating Token Index: 838