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

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

Neuron 3060 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5476. Min Range: -1.5476

Max Act: 1.5476. Min Act: -0.0000

Data Index: 1400638 (Python Code)

Max Activating Token Index: 670

Text #1

Max Range: 1.5476. Min Range: -1.5476

Max Act: 1.4017. Min Act: -0.0000

Data Index: 1538933 (Python Code)

Max Activating Token Index: 619

Text #2

Max Range: 1.5476. Min Range: -1.5476

Max Act: 1.2777. Min Act: -0.0000

Data Index: 1397481 (Python Code)

Max Activating Token Index: 894

Text #3

Max Range: 1.5476. Min Range: -1.5476

Max Act: 1.3708. Min Act: -0.0000

Data Index: 1600427 (Python Code)

Max Activating Token Index: 144

Text #4

Max Range: 1.5476. Min Range: -1.5476

Max Act: 1.2962. Min Act: -0.0000

Data Index: 1424761 (Python Code)

Max Activating Token Index: 506

Text #5

Max Range: 1.5476. Min Range: -1.5476

Max Act: 1.1959. Min Act: -0.0000

Data Index: 365356 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 1.5476. Min Range: -1.5476

Max Act: 1.2936. Min Act: -0.0000

Data Index: 1612503 (Python Code)

Max Activating Token Index: 312

Text #7

Max Range: 1.5476. Min Range: -1.5476

Max Act: 1.2101. Min Act: -0.0000

Data Index: 1517863 (Python Code)

Max Activating Token Index: 195

Text #8

Max Range: 1.5476. Min Range: -1.5476

Max Act: 1.1744. Min Act: -0.0000

Data Index: 1563601 (Python Code)

Max Activating Token Index: 382

Text #9

Max Range: 1.5476. Min Range: -1.5476

Max Act: 1.1296. Min Act: -0.0000

Data Index: 163156 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 1.5476. Min Range: -1.5476

Max Act: 1.1581. Min Act: -0.0000

Data Index: 1491946 (Python Code)

Max Activating Token Index: 450

Text #11

Max Range: 1.5476. Min Range: -1.5476

Max Act: 1.1117. Min Act: -0.0000

Data Index: 1432161 (Python Code)

Max Activating Token Index: 177

Text #12

Max Range: 1.5476. Min Range: -1.5476

Max Act: 1.1516. Min Act: -0.0000

Data Index: 1476654 (Python Code)

Max Activating Token Index: 292

Text #13

Max Range: 1.5476. Min Range: -1.5476

Max Act: 1.1036. Min Act: -0.0000

Data Index: 1539207 (Python Code)

Max Activating Token Index: 321

Text #14

Max Range: 1.5476. Min Range: -1.5476

Max Act: 1.1408. Min Act: -0.0000

Data Index: 1169459 (C4 (Web Text))

Max Activating Token Index: 955

Text #15

Max Range: 1.5476. Min Range: -1.5476

Max Act: 1.1018. Min Act: -0.0000

Data Index: 1425860 (Python Code)

Max Activating Token Index: 329

Text #16

Max Range: 1.5476. Min Range: -1.5476

Max Act: 1.1421. Min Act: -0.0000

Data Index: 1432067 (Python Code)

Max Activating Token Index: 384

Text #17

Max Range: 1.5476. Min Range: -1.5476

Max Act: 1.0992. Min Act: -0.0000

Data Index: 1583085 (Python Code)

Max Activating Token Index: 367

Text #18

Max Range: 1.5476. Min Range: -1.5476

Max Act: 1.1351. Min Act: -0.0000

Data Index: 132826 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 1.5476. Min Range: -1.5476

Max Act: 0.9696. Min Act: -0.0000

Data Index: 1530355 (Python Code)

Max Activating Token Index: 94