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

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

Neuron 1686 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2051. Min Range: -2.2051

Max Act: 2.2051. Min Act: -0.0000

Data Index: 340565 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 2.2051. Min Range: -2.2051

Max Act: 1.9128. Min Act: -0.0000

Data Index: 765102 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 2.2051. Min Range: -2.2051

Max Act: 1.9600. Min Act: -0.0000

Data Index: 238438 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 2.2051. Min Range: -2.2051

Max Act: 1.9806. Min Act: -0.0000

Data Index: 412696 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 2.2051. Min Range: -2.2051

Max Act: 1.6779. Min Act: -0.0000

Data Index: 369531 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 2.2051. Min Range: -2.2051

Max Act: 1.7708. Min Act: -0.0000

Data Index: 1543274 (Python Code)

Max Activating Token Index: 1003

Text #6

Max Range: 2.2051. Min Range: -2.2051

Max Act: 1.7753. Min Act: -0.0000

Data Index: 734868 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 2.2051. Min Range: -2.2051

Max Act: 1.7544. Min Act: -0.0000

Data Index: 237405 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 2.2051. Min Range: -2.2051

Max Act: 1.7267. Min Act: -0.0000

Data Index: 546087 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 2.2051. Min Range: -2.2051

Max Act: 1.9784. Min Act: -0.0000

Data Index: 433148 (C4 (Web Text))

Max Activating Token Index: 289

Text #10

Max Range: 2.2051. Min Range: -2.2051

Max Act: 1.6434. Min Act: -0.0000

Data Index: 1082048 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 2.2051. Min Range: -2.2051

Max Act: 1.7404. Min Act: -0.0000

Data Index: 293284 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 2.2051. Min Range: -2.2051

Max Act: 1.6603. Min Act: -0.0000

Data Index: 1034147 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 2.2051. Min Range: -2.2051

Max Act: 1.7340. Min Act: -0.0000

Data Index: 1038362 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 2.2051. Min Range: -2.2051

Max Act: 1.6109. Min Act: -0.0000

Data Index: 1301577 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 2.2051. Min Range: -2.2051

Max Act: 1.5994. Min Act: -0.0000

Data Index: 532191 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 2.2051. Min Range: -2.2051

Max Act: 1.4360. Min Act: -0.0000

Data Index: 111317 (C4 (Web Text))

Max Activating Token Index: 875

Text #17

Max Range: 2.2051. Min Range: -2.2051

Max Act: 1.4829. Min Act: -0.0000

Data Index: 1028576 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 2.2051. Min Range: -2.2051

Max Act: 1.5837. Min Act: -0.0000

Data Index: 1467172 (Python Code)

Max Activating Token Index: 657

Text #19

Max Range: 2.2051. Min Range: -2.2051

Max Act: 1.4908. Min Act: -0.0000

Data Index: 150258 (C4 (Web Text))

Max Activating Token Index: 803