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

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

Neuron 3484 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.3637. Min Act: -0.0001

Data Index: 667515 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2299. Min Act: -0.0001

Data Index: 293557 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2331. Min Act: -0.0001

Data Index: 1098903 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2273. Min Act: -0.0001

Data Index: 473166 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2257. Min Act: -0.0001

Data Index: 142370 (C4 (Web Text))

Max Activating Token Index: 967

Text #5

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2327. Min Act: -0.0001

Data Index: 786122 (C4 (Web Text))

Max Activating Token Index: 921

Text #6

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2011. Min Act: -0.0001

Data Index: 1097629 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2036. Min Act: -0.0001

Data Index: 652192 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.1936. Min Act: -0.0001

Data Index: 273593 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.1833. Min Act: -0.0001

Data Index: 1614311 (Python Code)

Max Activating Token Index: 837

Text #10

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.1925. Min Act: -0.0001

Data Index: 1325647 (C4 (Web Text))

Max Activating Token Index: 412

Text #11

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.1798. Min Act: -0.0001

Data Index: 1057182 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.1919. Min Act: -0.0001

Data Index: 270405 (C4 (Web Text))

Max Activating Token Index: 372

Text #13

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2130. Min Act: -0.0001

Data Index: 1212082 (C4 (Web Text))

Max Activating Token Index: 814

Text #14

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.1585. Min Act: -0.0001

Data Index: 393141 (C4 (Web Text))

Max Activating Token Index: 191

Text #15

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.1769. Min Act: -0.0001

Data Index: 1191759 (C4 (Web Text))

Max Activating Token Index: 612

Text #16

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.1738. Min Act: -0.0001

Data Index: 1465916 (Python Code)

Max Activating Token Index: 224

Text #17

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.1826. Min Act: -0.0001

Data Index: 1522199 (Python Code)

Max Activating Token Index: 18

Text #18

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.1919. Min Act: -0.0001

Data Index: 650555 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.1924. Min Act: -0.0001

Data Index: 820667 (C4 (Web Text))

Max Activating Token Index: 369