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

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

Neuron 4928 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.9648. Min Act: -0.0001

Data Index: 870627 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.8187. Min Act: -0.0001

Data Index: 1073793 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.8585. Min Act: -0.0001

Data Index: 1005389 (C4 (Web Text))

Max Activating Token Index: 354

Text #3

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.9127. Min Act: -0.0001

Data Index: 659278 (C4 (Web Text))

Max Activating Token Index: 292

Text #4

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.8073. Min Act: -0.0001

Data Index: 495303 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.8258. Min Act: -0.0001

Data Index: 377253 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.9414. Min Act: -0.0001

Data Index: 539383 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.7931. Min Act: -0.0001

Data Index: 143591 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.7140. Min Act: -0.0001

Data Index: 781294 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.6757. Min Act: -0.0001

Data Index: 883402 (C4 (Web Text))

Max Activating Token Index: 703

Text #10

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.7537. Min Act: -0.0001

Data Index: 66302 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.7559. Min Act: -0.0001

Data Index: 858226 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.7483. Min Act: -0.0001

Data Index: 1247377 (C4 (Web Text))

Max Activating Token Index: 289

Text #13

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.7263. Min Act: -0.0001

Data Index: 247295 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.7495. Min Act: -0.0001

Data Index: 1192834 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.7956. Min Act: -0.0001

Data Index: 111801 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.7516. Min Act: -0.0001

Data Index: 824119 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.7329. Min Act: -0.0001

Data Index: 1047687 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.7385. Min Act: -0.0001

Data Index: 571896 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.7370. Min Act: -0.0001

Data Index: 1022157 (C4 (Web Text))

Max Activating Token Index: 424