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

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

Neuron 3103 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: 0.8561. Min Range: -0.8561

Max Act: 0.8546. Min Act: -0.0000

Data Index: 1164135 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.8561. Min Act: -0.0000

Data Index: 1016570 (C4 (Web Text))

Max Activating Token Index: 437

Text #2

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.7190. Min Act: -0.0000

Data Index: 1229441 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.6587. Min Act: -0.0000

Data Index: 1096500 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.6437. Min Act: -0.0000

Data Index: 7927 (C4 (Web Text))

Max Activating Token Index: 1022

Text #5

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.6365. Min Act: -0.0000

Data Index: 648960 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.6586. Min Act: -0.0000

Data Index: 79151 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.6037. Min Act: -0.0000

Data Index: 952719 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.6184. Min Act: -0.0000

Data Index: 938572 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.6153. Min Act: -0.0000

Data Index: 152833 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.6425. Min Act: -0.0000

Data Index: 666461 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.5880. Min Act: -0.0000

Data Index: 774573 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.5532. Min Act: -0.0000

Data Index: 202246 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.6023. Min Act: -0.0000

Data Index: 79149 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.5292. Min Act: -0.0000

Data Index: 360140 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.5470. Min Act: -0.0000

Data Index: 1253974 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.5429. Min Act: -0.0000

Data Index: 552180 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.5348. Min Act: -0.0000

Data Index: 675229 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.5304. Min Act: -0.0000

Data Index: 1217848 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.8561. Min Range: -0.8561

Max Act: 0.5014. Min Act: -0.0000

Data Index: 947126 (C4 (Web Text))

Max Activating Token Index: 572