Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3494 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0247. Min Range: -1.0247

Max Act: 1.0247. Min Act: -0.0001

Data Index: 1374984 (Python Code)

Max Activating Token Index: 23

Text #1

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.9236. Min Act: -0.0001

Data Index: 1258143 (C4 (Web Text))

Max Activating Token Index: 903

Text #2

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.8482. Min Act: -0.0001

Data Index: 1508497 (Python Code)

Max Activating Token Index: 919

Text #3

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.7923. Min Act: -0.0001

Data Index: 1401272 (Python Code)

Max Activating Token Index: 225

Text #4

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.8158. Min Act: -0.0001

Data Index: 1403813 (Python Code)

Max Activating Token Index: 629

Text #5

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.8314. Min Act: -0.0001

Data Index: 1200756 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.7187. Min Act: -0.0001

Data Index: 1043574 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.7285. Min Act: -0.0001

Data Index: 1647650 (Python Code)

Max Activating Token Index: 66

Text #8

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.7465. Min Act: -0.0001

Data Index: 742586 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.7010. Min Act: -0.0001

Data Index: 1291944 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.7024. Min Act: -0.0001

Data Index: 1346391 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.6583. Min Act: -0.0001

Data Index: 160672 (C4 (Web Text))

Max Activating Token Index: 983

Text #12

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.7050. Min Act: -0.0001

Data Index: 1156265 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.7262. Min Act: -0.0001

Data Index: 611447 (C4 (Web Text))

Max Activating Token Index: 482

Text #14

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.7192. Min Act: -0.0001

Data Index: 275489 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.6465. Min Act: -0.0001

Data Index: 16475 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.6782. Min Act: -0.0001

Data Index: 194154 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.6436. Min Act: -0.0001

Data Index: 1140618 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.6574. Min Act: -0.0001

Data Index: 1614638 (Python Code)

Max Activating Token Index: 292

Text #19

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.6562. Min Act: -0.0001

Data Index: 1451714 (Python Code)

Max Activating Token Index: 630