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

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

Neuron 1670 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2849. Min Range: -1.2849

Max Act: 1.2849. Min Act: -0.0000

Data Index: 1609524 (Python Code)

Max Activating Token Index: 531

Text #1

Max Range: 1.2849. Min Range: -1.2849

Max Act: 1.2388. Min Act: -0.0000

Data Index: 1403231 (Python Code)

Max Activating Token Index: 134

Text #2

Max Range: 1.2849. Min Range: -1.2849

Max Act: 1.1855. Min Act: -0.0000

Data Index: 1638227 (Python Code)

Max Activating Token Index: 377

Text #3

Max Range: 1.2849. Min Range: -1.2849

Max Act: 1.0290. Min Act: -0.0000

Data Index: 1633322 (Python Code)

Max Activating Token Index: 157

Text #4

Max Range: 1.2849. Min Range: -1.2849

Max Act: 1.0367. Min Act: -0.0000

Data Index: 1524114 (Python Code)

Max Activating Token Index: 477

Text #5

Max Range: 1.2849. Min Range: -1.2849

Max Act: 1.0910. Min Act: -0.0000

Data Index: 1581996 (Python Code)

Max Activating Token Index: 206

Text #6

Max Range: 1.2849. Min Range: -1.2849

Max Act: 1.0902. Min Act: 0.0000

Data Index: 1360614 (Python Code)

Max Activating Token Index: 184

Text #7

Max Range: 1.2849. Min Range: -1.2849

Max Act: 1.0235. Min Act: -0.0000

Data Index: 1627966 (Python Code)

Max Activating Token Index: 652

Text #8

Max Range: 1.2849. Min Range: -1.2849

Max Act: 1.1180. Min Act: -0.0000

Data Index: 1404559 (Python Code)

Max Activating Token Index: 817

Text #9

Max Range: 1.2849. Min Range: -1.2849

Max Act: 0.9744. Min Act: 0.0000

Data Index: 1573673 (Python Code)

Max Activating Token Index: 356

Text #10

Max Range: 1.2849. Min Range: -1.2849

Max Act: 1.0345. Min Act: 0.0000

Data Index: 1652555 (Python Code)

Max Activating Token Index: 835

Text #11

Max Range: 1.2849. Min Range: -1.2849

Max Act: 0.9573. Min Act: 0.0000

Data Index: 1370481 (Python Code)

Max Activating Token Index: 580

Text #12

Max Range: 1.2849. Min Range: -1.2849

Max Act: 0.9548. Min Act: -0.0000

Data Index: 1625074 (Python Code)

Max Activating Token Index: 807

Text #13

Max Range: 1.2849. Min Range: -1.2849

Max Act: 0.8902. Min Act: 0.0000

Data Index: 1378941 (Python Code)

Max Activating Token Index: 51

Text #14

Max Range: 1.2849. Min Range: -1.2849

Max Act: 0.9383. Min Act: -0.0000

Data Index: 1522733 (Python Code)

Max Activating Token Index: 734

Text #15

Max Range: 1.2849. Min Range: -1.2849

Max Act: 0.8795. Min Act: -0.0000

Data Index: 1432523 (Python Code)

Max Activating Token Index: 579

Text #16

Max Range: 1.2849. Min Range: -1.2849

Max Act: 0.9117. Min Act: -0.0000

Data Index: 1446341 (Python Code)

Max Activating Token Index: 77

Text #17

Max Range: 1.2849. Min Range: -1.2849

Max Act: 0.9273. Min Act: -0.0000

Data Index: 1425152 (Python Code)

Max Activating Token Index: 881

Text #18

Max Range: 1.2849. Min Range: -1.2849

Max Act: 0.8428. Min Act: -0.0000

Data Index: 1566357 (Python Code)

Max Activating Token Index: 101

Text #19

Max Range: 1.2849. Min Range: -1.2849

Max Act: 0.8233. Min Act: -0.0000

Data Index: 1480188 (Python Code)

Max Activating Token Index: 123