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

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

Neuron 3252 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6789. Min Act: -0.0000

Data Index: 1553492 (Python Code)

Max Activating Token Index: 170

Text #1

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6937. Min Act: -0.0000

Data Index: 1463344 (Python Code)

Max Activating Token Index: 109

Text #2

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6186. Min Act: -0.0000

Data Index: 1432459 (Python Code)

Max Activating Token Index: 184

Text #3

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6721. Min Act: -0.0000

Data Index: 1538293 (Python Code)

Max Activating Token Index: 181

Text #4

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6022. Min Act: -0.0000

Data Index: 1499393 (Python Code)

Max Activating Token Index: 277

Text #5

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6355. Min Act: -0.0000

Data Index: 1498272 (Python Code)

Max Activating Token Index: 184

Text #6

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6112. Min Act: -0.0000

Data Index: 1652856 (Python Code)

Max Activating Token Index: 735

Text #7

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6066. Min Act: -0.0000

Data Index: 1523434 (Python Code)

Max Activating Token Index: 171

Text #8

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6435. Min Act: -0.0000

Data Index: 1603167 (Python Code)

Max Activating Token Index: 421

Text #9

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6032. Min Act: -0.0001

Data Index: 1362362 (Python Code)

Max Activating Token Index: 410

Text #10

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6039. Min Act: -0.0000

Data Index: 1516196 (Python Code)

Max Activating Token Index: 149

Text #11

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6328. Min Act: -0.0001

Data Index: 1449492 (Python Code)

Max Activating Token Index: 72

Text #12

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6115. Min Act: -0.0001

Data Index: 1393017 (Python Code)

Max Activating Token Index: 533

Text #13

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6067. Min Act: -0.0000

Data Index: 1451417 (Python Code)

Max Activating Token Index: 68

Text #14

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5818. Min Act: -0.0001

Data Index: 1430264 (Python Code)

Max Activating Token Index: 306

Text #15

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6174. Min Act: -0.0001

Data Index: 1453414 (Python Code)

Max Activating Token Index: 621

Text #16

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6129. Min Act: -0.0000

Data Index: 1486175 (Python Code)

Max Activating Token Index: 210

Text #17

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5698. Min Act: -0.0000

Data Index: 1478390 (Python Code)

Max Activating Token Index: 494

Text #18

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5881. Min Act: -0.0000

Data Index: 1361361 (Python Code)

Max Activating Token Index: 170

Text #19

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5352. Min Act: -0.0000

Data Index: 1426946 (Python Code)

Max Activating Token Index: 781