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

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

Neuron 3573 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9938. Min Range: -0.9938

Max Act: 0.9938. Min Act: -0.0000

Data Index: 270376 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 0.9938. Min Range: -0.9938

Max Act: 0.9344. Min Act: -0.0000

Data Index: 1253522 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 0.9938. Min Range: -0.9938

Max Act: 0.8508. Min Act: -0.0000

Data Index: 992901 (C4 (Web Text))

Max Activating Token Index: 814

Text #3

Max Range: 0.9938. Min Range: -0.9938

Max Act: 0.7398. Min Act: -0.0000

Data Index: 1647482 (Python Code)

Max Activating Token Index: 894

Text #4

Max Range: 0.9938. Min Range: -0.9938

Max Act: 0.8309. Min Act: -0.0000

Data Index: 1012010 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 0.9938. Min Range: -0.9938

Max Act: 0.8119. Min Act: -0.0000

Data Index: 1466827 (Python Code)

Max Activating Token Index: 862

Text #6

Max Range: 0.9938. Min Range: -0.9938

Max Act: 0.7028. Min Act: -0.0000

Data Index: 142016 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 0.9938. Min Range: -0.9938

Max Act: 0.7543. Min Act: -0.0000

Data Index: 776913 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 0.9938. Min Range: -0.9938

Max Act: 0.7850. Min Act: -0.0000

Data Index: 305446 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 0.9938. Min Range: -0.9938

Max Act: 0.7604. Min Act: -0.0000

Data Index: 94446 (C4 (Web Text))

Max Activating Token Index: 465

Text #10

Max Range: 0.9938. Min Range: -0.9938

Max Act: 0.7411. Min Act: -0.0000

Data Index: 751823 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 0.9938. Min Range: -0.9938

Max Act: 0.7764. Min Act: -0.0000

Data Index: 1594770 (Python Code)

Max Activating Token Index: 944

Text #12

Max Range: 0.9938. Min Range: -0.9938

Max Act: 0.7059. Min Act: -0.0000

Data Index: 11294 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 0.9938. Min Range: -0.9938

Max Act: 0.7093. Min Act: -0.0000

Data Index: 675280 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 0.9938. Min Range: -0.9938

Max Act: 0.7529. Min Act: -0.0000

Data Index: 1537140 (Python Code)

Max Activating Token Index: 880

Text #15

Max Range: 0.9938. Min Range: -0.9938

Max Act: 0.7414. Min Act: -0.0000

Data Index: 615187 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 0.9938. Min Range: -0.9938

Max Act: 0.6995. Min Act: -0.0000

Data Index: 841898 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 0.9938. Min Range: -0.9938

Max Act: 0.7042. Min Act: -0.0000

Data Index: 745621 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 0.9938. Min Range: -0.9938

Max Act: 0.6435. Min Act: -0.0000

Data Index: 1366521 (Python Code)

Max Activating Token Index: 666

Text #19

Max Range: 0.9938. Min Range: -0.9938

Max Act: 0.6731. Min Act: -0.0000

Data Index: 955312 (C4 (Web Text))

Max Activating Token Index: 752