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

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

Neuron 4467 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.4873. Min Act: -0.0000

Data Index: 1482629 (Python Code)

Max Activating Token Index: 31

Text #1

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.1674. Min Act: -0.0000

Data Index: 1524124 (Python Code)

Max Activating Token Index: 539

Text #2

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.0930. Min Act: -0.0000

Data Index: 1578147 (Python Code)

Max Activating Token Index: 386

Text #3

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.0827. Min Act: -0.0000

Data Index: 1457248 (Python Code)

Max Activating Token Index: 903

Text #4

Max Range: 1.4873. Min Range: -1.4873

Max Act: 0.9493. Min Act: -0.0000

Data Index: 1424206 (Python Code)

Max Activating Token Index: 960

Text #5

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.0746. Min Act: -0.0000

Data Index: 1365983 (Python Code)

Max Activating Token Index: 366

Text #6

Max Range: 1.4873. Min Range: -1.4873

Max Act: 0.9541. Min Act: -0.0000

Data Index: 1498427 (Python Code)

Max Activating Token Index: 668

Text #7

Max Range: 1.4873. Min Range: -1.4873

Max Act: 0.9682. Min Act: -0.0000

Data Index: 1505777 (Python Code)

Max Activating Token Index: 313

Text #8

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.0352. Min Act: -0.0000

Data Index: 1558005 (Python Code)

Max Activating Token Index: 313

Text #9

Max Range: 1.4873. Min Range: -1.4873

Max Act: 0.9523. Min Act: -0.0000

Data Index: 1488563 (Python Code)

Max Activating Token Index: 701

Text #10

Max Range: 1.4873. Min Range: -1.4873

Max Act: 0.9884. Min Act: -0.0000

Data Index: 1409818 (Python Code)

Max Activating Token Index: 278

Text #11

Max Range: 1.4873. Min Range: -1.4873

Max Act: 0.9999. Min Act: -0.0000

Data Index: 1382568 (Python Code)

Max Activating Token Index: 266

Text #12

Max Range: 1.4873. Min Range: -1.4873

Max Act: 0.9991. Min Act: -0.0000

Data Index: 1419368 (Python Code)

Max Activating Token Index: 222

Text #13

Max Range: 1.4873. Min Range: -1.4873

Max Act: 0.9944. Min Act: -0.0000

Data Index: 1521355 (Python Code)

Max Activating Token Index: 586

Text #14

Max Range: 1.4873. Min Range: -1.4873

Max Act: 0.9813. Min Act: -0.0000

Data Index: 1454676 (Python Code)

Max Activating Token Index: 473

Text #15

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.0020. Min Act: -0.0000

Data Index: 1362547 (Python Code)

Max Activating Token Index: 346

Text #16

Max Range: 1.4873. Min Range: -1.4873

Max Act: 0.9797. Min Act: -0.0000

Data Index: 1398083 (Python Code)

Max Activating Token Index: 686

Text #17

Max Range: 1.4873. Min Range: -1.4873

Max Act: 0.9653. Min Act: -0.0000

Data Index: 1429897 (Python Code)

Max Activating Token Index: 116

Text #18

Max Range: 1.4873. Min Range: -1.4873

Max Act: 0.9439. Min Act: -0.0000

Data Index: 1370552 (Python Code)

Max Activating Token Index: 375

Text #19

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.0039. Min Act: -0.0000

Data Index: 1468694 (Python Code)

Max Activating Token Index: 261