Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 168 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3905. Min Range: -1.3905

Max Act: 1.3905. Min Act: -0.0001

Data Index: 673899 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 1.3905. Min Range: -1.3905

Max Act: 1.1291. Min Act: -0.0001

Data Index: 1517300 (Python Code)

Max Activating Token Index: 1006

Text #2

Max Range: 1.3905. Min Range: -1.3905

Max Act: 1.1878. Min Act: -0.0001

Data Index: 485558 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 1.3905. Min Range: -1.3905

Max Act: 1.1912. Min Act: -0.0001

Data Index: 1526630 (Python Code)

Max Activating Token Index: 726

Text #4

Max Range: 1.3905. Min Range: -1.3905

Max Act: 1.0389. Min Act: -0.0001

Data Index: 706734 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 1.3905. Min Range: -1.3905

Max Act: 0.9880. Min Act: -0.0001

Data Index: 750424 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 1.3905. Min Range: -1.3905

Max Act: 0.9401. Min Act: -0.0001

Data Index: 1384772 (Python Code)

Max Activating Token Index: 752

Text #7

Max Range: 1.3905. Min Range: -1.3905

Max Act: 1.0764. Min Act: -0.0000

Data Index: 615622 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 1.3905. Min Range: -1.3905

Max Act: 0.9800. Min Act: -0.0001

Data Index: 674571 (C4 (Web Text))

Max Activating Token Index: 247

Text #9

Max Range: 1.3905. Min Range: -1.3905

Max Act: 0.9177. Min Act: -0.0001

Data Index: 137995 (C4 (Web Text))

Max Activating Token Index: 338

Text #10

Max Range: 1.3905. Min Range: -1.3905

Max Act: 0.9516. Min Act: -0.0000

Data Index: 499089 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 1.3905. Min Range: -1.3905

Max Act: 0.9145. Min Act: -0.0000

Data Index: 593767 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 1.3905. Min Range: -1.3905

Max Act: 0.8857. Min Act: -0.0001

Data Index: 545791 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 1.3905. Min Range: -1.3905

Max Act: 0.9236. Min Act: -0.0001

Data Index: 1097826 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 1.3905. Min Range: -1.3905

Max Act: 0.8589. Min Act: -0.0001

Data Index: 1377401 (Python Code)

Max Activating Token Index: 600

Text #15

Max Range: 1.3905. Min Range: -1.3905

Max Act: 0.8430. Min Act: -0.0001

Data Index: 1359768 (C4 (Web Text))

Max Activating Token Index: 983

Text #16

Max Range: 1.3905. Min Range: -1.3905

Max Act: 0.8980. Min Act: -0.0000

Data Index: 644735 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 1.3905. Min Range: -1.3905

Max Act: 0.8896. Min Act: -0.0000

Data Index: 1072160 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 1.3905. Min Range: -1.3905

Max Act: 0.7729. Min Act: -0.0000

Data Index: 184518 (C4 (Web Text))

Max Activating Token Index: 757

Text #19

Max Range: 1.3905. Min Range: -1.3905

Max Act: 0.8820. Min Act: -0.0001

Data Index: 51586 (C4 (Web Text))

Max Activating Token Index: 160