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

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

Neuron 2973 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: 1.5449. Min Range: -1.5449

Max Act: 1.5449. Min Act: -0.0000

Data Index: 256272 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 1.5449. Min Range: -1.5449

Max Act: 1.2014. Min Act: -0.0000

Data Index: 708362 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 1.5449. Min Range: -1.5449

Max Act: 1.1159. Min Act: -0.0001

Data Index: 1016526 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 1.5449. Min Range: -1.5449

Max Act: 1.0564. Min Act: -0.0000

Data Index: 1579825 (Python Code)

Max Activating Token Index: 355

Text #4

Max Range: 1.5449. Min Range: -1.5449

Max Act: 1.0338. Min Act: -0.0001

Data Index: 395630 (C4 (Web Text))

Max Activating Token Index: 915

Text #5

Max Range: 1.5449. Min Range: -1.5449

Max Act: 0.9942. Min Act: -0.0000

Data Index: 1192490 (C4 (Web Text))

Max Activating Token Index: 365

Text #6

Max Range: 1.5449. Min Range: -1.5449

Max Act: 1.0314. Min Act: -0.0000

Data Index: 1389646 (Python Code)

Max Activating Token Index: 323

Text #7

Max Range: 1.5449. Min Range: -1.5449

Max Act: 0.8900. Min Act: -0.0000

Data Index: 1535760 (Python Code)

Max Activating Token Index: 885

Text #8

Max Range: 1.5449. Min Range: -1.5449

Max Act: 1.0396. Min Act: -0.0000

Data Index: 1029465 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 1.5449. Min Range: -1.5449

Max Act: 0.9521. Min Act: -0.0000

Data Index: 1620678 (Python Code)

Max Activating Token Index: 678

Text #10

Max Range: 1.5449. Min Range: -1.5449

Max Act: 0.8569. Min Act: -0.0000

Data Index: 1546775 (Python Code)

Max Activating Token Index: 374

Text #11

Max Range: 1.5449. Min Range: -1.5449

Max Act: 0.9660. Min Act: -0.0000

Data Index: 242257 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 1.5449. Min Range: -1.5449

Max Act: 0.8675. Min Act: -0.0000

Data Index: 1570682 (Python Code)

Max Activating Token Index: 176

Text #13

Max Range: 1.5449. Min Range: -1.5449

Max Act: 0.8824. Min Act: -0.0000

Data Index: 1494330 (Python Code)

Max Activating Token Index: 633

Text #14

Max Range: 1.5449. Min Range: -1.5449

Max Act: 0.9061. Min Act: -0.0000

Data Index: 1577542 (Python Code)

Max Activating Token Index: 999

Text #15

Max Range: 1.5449. Min Range: -1.5449

Max Act: 0.8661. Min Act: -0.0000

Data Index: 210628 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 1.5449. Min Range: -1.5449

Max Act: 0.8793. Min Act: -0.0000

Data Index: 1472825 (Python Code)

Max Activating Token Index: 158

Text #17

Max Range: 1.5449. Min Range: -1.5449

Max Act: 0.9444. Min Act: -0.0000

Data Index: 883699 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 1.5449. Min Range: -1.5449

Max Act: 0.8512. Min Act: -0.0000

Data Index: 336501 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 1.5449. Min Range: -1.5449

Max Act: 0.8754. Min Act: -0.0000

Data Index: 1361447 (Python Code)

Max Activating Token Index: 614