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

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

Neuron 5535 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5328. Min Range: -5.5328

Max Act: 5.5328. Min Act: -0.0000

Data Index: 1173100 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 5.5328. Min Range: -5.5328

Max Act: 5.3196. Min Act: -0.0000

Data Index: 1078544 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 5.5328. Min Range: -5.5328

Max Act: 5.3818. Min Act: -0.0000

Data Index: 1000059 (C4 (Web Text))

Max Activating Token Index: 263

Text #3

Max Range: 5.5328. Min Range: -5.5328

Max Act: 5.5301. Min Act: -0.0000

Data Index: 853438 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 5.5328. Min Range: -5.5328

Max Act: 5.0416. Min Act: -0.0000

Data Index: 1075339 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 5.5328. Min Range: -5.5328

Max Act: 5.0415. Min Act: -0.0000

Data Index: 968576 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 5.5328. Min Range: -5.5328

Max Act: 5.2267. Min Act: -0.0000

Data Index: 503013 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 5.5328. Min Range: -5.5328

Max Act: 5.1732. Min Act: -0.0000

Data Index: 1029004 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 5.5328. Min Range: -5.5328

Max Act: 4.9751. Min Act: -0.0000

Data Index: 1000695 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 5.5328. Min Range: -5.5328

Max Act: 4.7708. Min Act: -0.0000

Data Index: 1254078 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 5.5328. Min Range: -5.5328

Max Act: 4.9431. Min Act: -0.0000

Data Index: 776135 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 5.5328. Min Range: -5.5328

Max Act: 4.8277. Min Act: -0.0000

Data Index: 1198279 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 5.5328. Min Range: -5.5328

Max Act: 5.0331. Min Act: -0.0000

Data Index: 1027865 (C4 (Web Text))

Max Activating Token Index: 577

Text #13

Max Range: 5.5328. Min Range: -5.5328

Max Act: 5.0374. Min Act: -0.0000

Data Index: 1191081 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 5.5328. Min Range: -5.5328

Max Act: 4.6194. Min Act: -0.0000

Data Index: 1357785 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 5.5328. Min Range: -5.5328

Max Act: 4.8180. Min Act: -0.0000

Data Index: 1201631 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 5.5328. Min Range: -5.5328

Max Act: 4.7888. Min Act: -0.0000

Data Index: 673145 (C4 (Web Text))

Max Activating Token Index: 379

Text #17

Max Range: 5.5328. Min Range: -5.5328

Max Act: 4.7335. Min Act: -0.0000

Data Index: 969336 (C4 (Web Text))

Max Activating Token Index: 186

Text #18

Max Range: 5.5328. Min Range: -5.5328

Max Act: 4.7701. Min Act: -0.0000

Data Index: 982680 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 5.5328. Min Range: -5.5328

Max Act: 4.9541. Min Act: -0.0000

Data Index: 997530 (C4 (Web Text))

Max Activating Token Index: 173