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

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

Neuron 2494 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: 1.1317. Min Range: -1.1317

Max Act: 1.1317. Min Act: -0.0000

Data Index: 1591187 (Python Code)

Max Activating Token Index: 904

Text #1

Max Range: 1.1317. Min Range: -1.1317

Max Act: 0.8497. Min Act: -0.0001

Data Index: 218294 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 1.1317. Min Range: -1.1317

Max Act: 0.9196. Min Act: -0.0000

Data Index: 723335 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 1.1317. Min Range: -1.1317

Max Act: 0.8536. Min Act: -0.0000

Data Index: 93812 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 1.1317. Min Range: -1.1317

Max Act: 0.8451. Min Act: -0.0001

Data Index: 1438679 (Python Code)

Max Activating Token Index: 391

Text #5

Max Range: 1.1317. Min Range: -1.1317

Max Act: 0.7906. Min Act: -0.0000

Data Index: 1620177 (Python Code)

Max Activating Token Index: 623

Text #6

Max Range: 1.1317. Min Range: -1.1317

Max Act: 0.7563. Min Act: -0.0000

Data Index: 1499674 (Python Code)

Max Activating Token Index: 863

Text #7

Max Range: 1.1317. Min Range: -1.1317

Max Act: 0.7759. Min Act: -0.0001

Data Index: 1408762 (Python Code)

Max Activating Token Index: 304

Text #8

Max Range: 1.1317. Min Range: -1.1317

Max Act: 0.7580. Min Act: -0.0001

Data Index: 1400434 (Python Code)

Max Activating Token Index: 344

Text #9

Max Range: 1.1317. Min Range: -1.1317

Max Act: 0.7492. Min Act: -0.0000

Data Index: 1637159 (Python Code)

Max Activating Token Index: 996

Text #10

Max Range: 1.1317. Min Range: -1.1317

Max Act: 0.7370. Min Act: -0.0001

Data Index: 1540238 (Python Code)

Max Activating Token Index: 191

Text #11

Max Range: 1.1317. Min Range: -1.1317

Max Act: 0.7357. Min Act: -0.0000

Data Index: 1450080 (Python Code)

Max Activating Token Index: 480

Text #12

Max Range: 1.1317. Min Range: -1.1317

Max Act: 0.6870. Min Act: -0.0000

Data Index: 838995 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 1.1317. Min Range: -1.1317

Max Act: 0.6544. Min Act: -0.0001

Data Index: 773887 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 1.1317. Min Range: -1.1317

Max Act: 0.6886. Min Act: -0.0000

Data Index: 1389100 (Python Code)

Max Activating Token Index: 350

Text #15

Max Range: 1.1317. Min Range: -1.1317

Max Act: 0.7197. Min Act: -0.0001

Data Index: 1574087 (Python Code)

Max Activating Token Index: 81

Text #16

Max Range: 1.1317. Min Range: -1.1317

Max Act: 0.6748. Min Act: -0.0001

Data Index: 1127840 (C4 (Web Text))

Max Activating Token Index: 836

Text #17

Max Range: 1.1317. Min Range: -1.1317

Max Act: 0.6658. Min Act: -0.0000

Data Index: 1394460 (Python Code)

Max Activating Token Index: 833

Text #18

Max Range: 1.1317. Min Range: -1.1317

Max Act: 0.7157. Min Act: -0.0000

Data Index: 1629852 (Python Code)

Max Activating Token Index: 908

Text #19

Max Range: 1.1317. Min Range: -1.1317

Max Act: 0.6845. Min Act: -0.0000

Data Index: 1391502 (Python Code)

Max Activating Token Index: 649