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

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

Neuron 2123 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6431. Min Range: -1.6431

Max Act: 1.6431. Min Act: -0.0000

Data Index: 1645609 (Python Code)

Max Activating Token Index: 968

Text #1

Max Range: 1.6431. Min Range: -1.6431

Max Act: 1.4348. Min Act: -0.0000

Data Index: 1646746 (Python Code)

Max Activating Token Index: 152

Text #2

Max Range: 1.6431. Min Range: -1.6431

Max Act: 1.4160. Min Act: -0.0000

Data Index: 1501636 (Python Code)

Max Activating Token Index: 185

Text #3

Max Range: 1.6431. Min Range: -1.6431

Max Act: 1.3671. Min Act: -0.0000

Data Index: 1654557 (Python Code)

Max Activating Token Index: 154

Text #4

Max Range: 1.6431. Min Range: -1.6431

Max Act: 1.3720. Min Act: -0.0000

Data Index: 1409590 (Python Code)

Max Activating Token Index: 846

Text #5

Max Range: 1.6431. Min Range: -1.6431

Max Act: 1.3575. Min Act: -0.0000

Data Index: 1597649 (Python Code)

Max Activating Token Index: 246

Text #6

Max Range: 1.6431. Min Range: -1.6431

Max Act: 1.2824. Min Act: -0.0000

Data Index: 1600133 (Python Code)

Max Activating Token Index: 663

Text #7

Max Range: 1.6431. Min Range: -1.6431

Max Act: 1.2650. Min Act: -0.0000

Data Index: 1467328 (Python Code)

Max Activating Token Index: 452

Text #8

Max Range: 1.6431. Min Range: -1.6431

Max Act: 1.2289. Min Act: -0.0000

Data Index: 1413863 (Python Code)

Max Activating Token Index: 350

Text #9

Max Range: 1.6431. Min Range: -1.6431

Max Act: 1.2914. Min Act: -0.0000

Data Index: 1371630 (Python Code)

Max Activating Token Index: 650

Text #10

Max Range: 1.6431. Min Range: -1.6431

Max Act: 1.3290. Min Act: -0.0000

Data Index: 1572877 (Python Code)

Max Activating Token Index: 879

Text #11

Max Range: 1.6431. Min Range: -1.6431

Max Act: 1.2134. Min Act: -0.0000

Data Index: 1359916 (Python Code)

Max Activating Token Index: 86

Text #12

Max Range: 1.6431. Min Range: -1.6431

Max Act: 1.2684. Min Act: -0.0000

Data Index: 1641119 (Python Code)

Max Activating Token Index: 285

Text #13

Max Range: 1.6431. Min Range: -1.6431

Max Act: 1.2230. Min Act: -0.0000

Data Index: 1379354 (Python Code)

Max Activating Token Index: 541

Text #14

Max Range: 1.6431. Min Range: -1.6431

Max Act: 1.2140. Min Act: -0.0000

Data Index: 1360165 (Python Code)

Max Activating Token Index: 782

Text #15

Max Range: 1.6431. Min Range: -1.6431

Max Act: 1.1401. Min Act: -0.0000

Data Index: 1457507 (Python Code)

Max Activating Token Index: 946

Text #16

Max Range: 1.6431. Min Range: -1.6431

Max Act: 1.2425. Min Act: -0.0000

Data Index: 1517365 (Python Code)

Max Activating Token Index: 924

Text #17

Max Range: 1.6431. Min Range: -1.6431

Max Act: 1.1576. Min Act: -0.0000

Data Index: 1547056 (Python Code)

Max Activating Token Index: 903

Text #18

Max Range: 1.6431. Min Range: -1.6431

Max Act: 1.1912. Min Act: -0.0000

Data Index: 1650008 (Python Code)

Max Activating Token Index: 629

Text #19

Max Range: 1.6431. Min Range: -1.6431

Max Act: 1.2125. Min Act: -0.0000

Data Index: 1398658 (Python Code)

Max Activating Token Index: 41