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

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

Neuron 894 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2540. Min Range: -3.2540

Max Act: 3.1297. Min Act: -0.0001

Data Index: 1475014 (Python Code)

Max Activating Token Index: 107

Text #1

Max Range: 3.2540. Min Range: -3.2540

Max Act: 3.2540. Min Act: -0.0001

Data Index: 55135 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 3.2540. Min Range: -3.2540

Max Act: 2.9241. Min Act: -0.0001

Data Index: 1223988 (C4 (Web Text))

Max Activating Token Index: 473

Text #3

Max Range: 3.2540. Min Range: -3.2540

Max Act: 3.0514. Min Act: -0.0001

Data Index: 851366 (C4 (Web Text))

Max Activating Token Index: 486

Text #4

Max Range: 3.2540. Min Range: -3.2540

Max Act: 3.0594. Min Act: -0.0001

Data Index: 422147 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 3.2540. Min Range: -3.2540

Max Act: 2.9052. Min Act: -0.0001

Data Index: 244618 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 3.2540. Min Range: -3.2540

Max Act: 3.0298. Min Act: -0.0001

Data Index: 1480409 (Python Code)

Max Activating Token Index: 165

Text #7

Max Range: 3.2540. Min Range: -3.2540

Max Act: 3.0279. Min Act: -0.0001

Data Index: 1145149 (C4 (Web Text))

Max Activating Token Index: 450

Text #8

Max Range: 3.2540. Min Range: -3.2540

Max Act: 3.0224. Min Act: -0.0001

Data Index: 80274 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 3.2540. Min Range: -3.2540

Max Act: 3.0946. Min Act: -0.0001

Data Index: 1567519 (Python Code)

Max Activating Token Index: 639

Text #10

Max Range: 3.2540. Min Range: -3.2540

Max Act: 2.7994. Min Act: -0.0001

Data Index: 1600439 (Python Code)

Max Activating Token Index: 261

Text #11

Max Range: 3.2540. Min Range: -3.2540

Max Act: 2.8362. Min Act: -0.0001

Data Index: 1588426 (Python Code)

Max Activating Token Index: 186

Text #12

Max Range: 3.2540. Min Range: -3.2540

Max Act: 3.0798. Min Act: -0.0001

Data Index: 1284177 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 3.2540. Min Range: -3.2540

Max Act: 2.8062. Min Act: -0.0001

Data Index: 1389798 (Python Code)

Max Activating Token Index: 321

Text #14

Max Range: 3.2540. Min Range: -3.2540

Max Act: 2.8248. Min Act: -0.0001

Data Index: 1604700 (Python Code)

Max Activating Token Index: 307

Text #15

Max Range: 3.2540. Min Range: -3.2540

Max Act: 2.7921. Min Act: -0.0001

Data Index: 1470387 (Python Code)

Max Activating Token Index: 203

Text #16

Max Range: 3.2540. Min Range: -3.2540

Max Act: 3.0847. Min Act: -0.0001

Data Index: 1459537 (Python Code)

Max Activating Token Index: 788

Text #17

Max Range: 3.2540. Min Range: -3.2540

Max Act: 2.9012. Min Act: -0.0001

Data Index: 635337 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 3.2540. Min Range: -3.2540

Max Act: 2.8837. Min Act: -0.0001

Data Index: 1656829 (Python Code)

Max Activating Token Index: 981

Text #19

Max Range: 3.2540. Min Range: -3.2540

Max Act: 2.9063. Min Act: -0.0001

Data Index: 447246 (C4 (Web Text))

Max Activating Token Index: 574