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

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

Neuron 4247 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.8200. Min Act: 0.0000

Data Index: 955232 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.1598. Min Act: -0.0000

Data Index: 1375174 (Python Code)

Max Activating Token Index: 599

Text #2

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.1861. Min Act: 0.0000

Data Index: 1242276 (C4 (Web Text))

Max Activating Token Index: 533

Text #3

Max Range: 1.8200. Min Range: -1.8200

Max Act: 0.8288. Min Act: -0.0000

Data Index: 1438216 (Python Code)

Max Activating Token Index: 294

Text #4

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.0443. Min Act: -0.0000

Data Index: 169415 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.0344. Min Act: -0.0000

Data Index: 1117808 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.0606. Min Act: -0.0000

Data Index: 339492 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.0120. Min Act: -0.0000

Data Index: 427079 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.0062. Min Act: -0.0000

Data Index: 1637367 (Python Code)

Max Activating Token Index: 639

Text #9

Max Range: 1.8200. Min Range: -1.8200

Max Act: 0.9582. Min Act: -0.0000

Data Index: 756766 (C4 (Web Text))

Max Activating Token Index: 474

Text #10

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.2156. Min Act: -0.0000

Data Index: 1511031 (Python Code)

Max Activating Token Index: 852

Text #11

Max Range: 1.8200. Min Range: -1.8200

Max Act: 0.9123. Min Act: -0.0000

Data Index: 728388 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 1.8200. Min Range: -1.8200

Max Act: 1.0339. Min Act: -0.0000

Data Index: 1378797 (Python Code)

Max Activating Token Index: 800

Text #13

Max Range: 1.8200. Min Range: -1.8200

Max Act: 0.9501. Min Act: -0.0000

Data Index: 852175 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 1.8200. Min Range: -1.8200

Max Act: 0.7785. Min Act: 0.0000

Data Index: 747289 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 1.8200. Min Range: -1.8200

Max Act: 0.8250. Min Act: 0.0001

Data Index: 491756 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 1.8200. Min Range: -1.8200

Max Act: 0.8445. Min Act: -0.0000

Data Index: 1141011 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 1.8200. Min Range: -1.8200

Max Act: 0.7778. Min Act: -0.0000

Data Index: 1265908 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 1.8200. Min Range: -1.8200

Max Act: 0.8198. Min Act: -0.0000

Data Index: 1168657 (C4 (Web Text))

Max Activating Token Index: 706

Text #19

Max Range: 1.8200. Min Range: -1.8200

Max Act: 0.8353. Min Act: 0.0000

Data Index: 1044035 (C4 (Web Text))

Max Activating Token Index: 962