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

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

Neuron 3740 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: 1.5509. Min Range: -1.5509

Max Act: 1.5509. Min Act: -0.0001

Data Index: 315404 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 1.5509. Min Range: -1.5509

Max Act: 1.4478. Min Act: -0.0001

Data Index: 535353 (C4 (Web Text))

Max Activating Token Index: 523

Text #2

Max Range: 1.5509. Min Range: -1.5509

Max Act: 1.4194. Min Act: -0.0001

Data Index: 1456706 (Python Code)

Max Activating Token Index: 205

Text #3

Max Range: 1.5509. Min Range: -1.5509

Max Act: 1.2595. Min Act: -0.0001

Data Index: 1503 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 1.5509. Min Range: -1.5509

Max Act: 1.2830. Min Act: -0.0001

Data Index: 710172 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 1.5509. Min Range: -1.5509

Max Act: 1.2162. Min Act: -0.0001

Data Index: 1264281 (C4 (Web Text))

Max Activating Token Index: 720

Text #6

Max Range: 1.5509. Min Range: -1.5509

Max Act: 1.1486. Min Act: -0.0001

Data Index: 100594 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 1.5509. Min Range: -1.5509

Max Act: 1.2084. Min Act: -0.0001

Data Index: 1347705 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 1.5509. Min Range: -1.5509

Max Act: 1.0053. Min Act: -0.0001

Data Index: 136286 (C4 (Web Text))

Max Activating Token Index: 234

Text #9

Max Range: 1.5509. Min Range: -1.5509

Max Act: 1.1591. Min Act: -0.0001

Data Index: 1359640 (C4 (Web Text))

Max Activating Token Index: 673

Text #10

Max Range: 1.5509. Min Range: -1.5509

Max Act: 1.1196. Min Act: -0.0001

Data Index: 79054 (C4 (Web Text))

Max Activating Token Index: 905

Text #11

Max Range: 1.5509. Min Range: -1.5509

Max Act: 1.0439. Min Act: -0.0001

Data Index: 1166508 (C4 (Web Text))

Max Activating Token Index: 1016

Text #12

Max Range: 1.5509. Min Range: -1.5509

Max Act: 0.9827. Min Act: -0.0001

Data Index: 1429504 (Python Code)

Max Activating Token Index: 617

Text #13

Max Range: 1.5509. Min Range: -1.5509

Max Act: 1.1017. Min Act: -0.0001

Data Index: 252515 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 1.5509. Min Range: -1.5509

Max Act: 1.0539. Min Act: -0.0001

Data Index: 1376828 (Python Code)

Max Activating Token Index: 672

Text #15

Max Range: 1.5509. Min Range: -1.5509

Max Act: 1.0441. Min Act: -0.0001

Data Index: 595128 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 1.5509. Min Range: -1.5509

Max Act: 1.0206. Min Act: -0.0001

Data Index: 1545900 (Python Code)

Max Activating Token Index: 331

Text #17

Max Range: 1.5509. Min Range: -1.5509

Max Act: 1.0429. Min Act: -0.0001

Data Index: 542199 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 1.5509. Min Range: -1.5509

Max Act: 1.0363. Min Act: -0.0001

Data Index: 1345195 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 1.5509. Min Range: -1.5509

Max Act: 1.1168. Min Act: -0.0001

Data Index: 1317961 (C4 (Web Text))

Max Activating Token Index: 826