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

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

Neuron 2559 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.5417. Min Act: -0.0000

Data Index: 42225 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.5187. Min Act: -0.0000

Data Index: 149129 (C4 (Web Text))

Max Activating Token Index: 737

Text #2

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.5034. Min Act: -0.0000

Data Index: 1490345 (Python Code)

Max Activating Token Index: 79

Text #3

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.3641. Min Act: -0.0000

Data Index: 765186 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.3304. Min Act: -0.0000

Data Index: 650152 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.3686. Min Act: -0.0000

Data Index: 657818 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.2490. Min Act: -0.0000

Data Index: 972695 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.3660. Min Act: 0.0000

Data Index: 356453 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.2548. Min Act: -0.0000

Data Index: 149468 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.2382. Min Act: -0.0000

Data Index: 567702 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.1634. Min Act: -0.0000

Data Index: 1584706 (Python Code)

Max Activating Token Index: 763

Text #11

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.1244. Min Act: -0.0000

Data Index: 735104 (C4 (Web Text))

Max Activating Token Index: 622

Text #12

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.1410. Min Act: -0.0000

Data Index: 261057 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.1498. Min Act: -0.0000

Data Index: 363030 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.1402. Min Act: -0.0000

Data Index: 430250 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.0934. Min Act: -0.0000

Data Index: 663284 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.1175. Min Act: -0.0000

Data Index: 149783 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.0841. Min Act: -0.0000

Data Index: 1466175 (Python Code)

Max Activating Token Index: 64

Text #18

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.1427. Min Act: -0.0000

Data Index: 659352 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 1.5417. Min Range: -1.5417

Max Act: 0.9885. Min Act: -0.0000

Data Index: 484282 (C4 (Web Text))

Max Activating Token Index: 217