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

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

Neuron 530 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.3080. Min Act: -0.0000

Data Index: 436443 (C4 (Web Text))

Max Activating Token Index: 710

Text #1

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.2194. Min Act: -0.0000

Data Index: 981363 (C4 (Web Text))

Max Activating Token Index: 969

Text #2

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.2118. Min Act: -0.0000

Data Index: 9163 (C4 (Web Text))

Max Activating Token Index: 988

Text #3

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.2367. Min Act: -0.0000

Data Index: 590649 (C4 (Web Text))

Max Activating Token Index: 705

Text #4

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.2407. Min Act: -0.0000

Data Index: 781162 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.2491. Min Act: -0.0000

Data Index: 1155648 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.1944. Min Act: -0.0000

Data Index: 1294637 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.1239. Min Act: -0.0000

Data Index: 260691 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.1635. Min Act: -0.0000

Data Index: 908852 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.1874. Min Act: -0.0000

Data Index: 1269240 (C4 (Web Text))

Max Activating Token Index: 771

Text #10

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.1682. Min Act: -0.0000

Data Index: 1125984 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.0908. Min Act: -0.0000

Data Index: 770287 (C4 (Web Text))

Max Activating Token Index: 171

Text #12

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.0613. Min Act: -0.0000

Data Index: 88628 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.1728. Min Act: -0.0000

Data Index: 428428 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.0569. Min Act: -0.0000

Data Index: 979691 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.1093. Min Act: -0.0000

Data Index: 1309695 (C4 (Web Text))

Max Activating Token Index: 816

Text #16

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.0685. Min Act: -0.0000

Data Index: 476442 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.0956. Min Act: -0.0000

Data Index: 933092 (C4 (Web Text))

Max Activating Token Index: 269

Text #18

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.0704. Min Act: -0.0000

Data Index: 414414 (C4 (Web Text))

Max Activating Token Index: 721

Text #19

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.0996. Min Act: -0.0000

Data Index: 567981 (C4 (Web Text))

Max Activating Token Index: 323