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

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

Neuron 4951 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: 0.2899. Min Range: -0.2899

Max Act: 0.2837. Min Act: -0.0000

Data Index: 1409292 (Python Code)

Max Activating Token Index: 517

Text #1

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2708. Min Act: -0.0000

Data Index: 1651687 (Python Code)

Max Activating Token Index: 944

Text #2

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2751. Min Act: -0.0000

Data Index: 1609970 (Python Code)

Max Activating Token Index: 215

Text #3

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2739. Min Act: -0.0000

Data Index: 1522673 (Python Code)

Max Activating Token Index: 259

Text #4

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2899. Min Act: -0.0000

Data Index: 1443459 (Python Code)

Max Activating Token Index: 704

Text #5

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2392. Min Act: -0.0000

Data Index: 1429014 (Python Code)

Max Activating Token Index: 691

Text #6

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2705. Min Act: -0.0000

Data Index: 1388864 (Python Code)

Max Activating Token Index: 177

Text #7

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2498. Min Act: -0.0000

Data Index: 1563454 (Python Code)

Max Activating Token Index: 382

Text #8

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2558. Min Act: -0.0000

Data Index: 1457718 (Python Code)

Max Activating Token Index: 62

Text #9

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2673. Min Act: -0.0000

Data Index: 1404999 (Python Code)

Max Activating Token Index: 313

Text #10

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2493. Min Act: -0.0000

Data Index: 1398539 (Python Code)

Max Activating Token Index: 309

Text #11

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2591. Min Act: -0.0000

Data Index: 1654420 (Python Code)

Max Activating Token Index: 225

Text #12

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2235. Min Act: -0.0000

Data Index: 1506045 (Python Code)

Max Activating Token Index: 725

Text #13

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2378. Min Act: -0.0000

Data Index: 1414219 (Python Code)

Max Activating Token Index: 1002

Text #14

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2401. Min Act: -0.0000

Data Index: 1545952 (Python Code)

Max Activating Token Index: 546

Text #15

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2377. Min Act: -0.0000

Data Index: 1360824 (Python Code)

Max Activating Token Index: 864

Text #16

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2355. Min Act: -0.0000

Data Index: 1480112 (Python Code)

Max Activating Token Index: 96

Text #17

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2392. Min Act: -0.0000

Data Index: 1363037 (Python Code)

Max Activating Token Index: 121

Text #18

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2355. Min Act: -0.0000

Data Index: 1524299 (Python Code)

Max Activating Token Index: 121

Text #19

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2539. Min Act: -0.0000

Data Index: 1639261 (Python Code)

Max Activating Token Index: 231