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

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

Neuron 4783 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.6925. Min Act: -0.0000

Data Index: 921733 (C4 (Web Text))

Max Activating Token Index: 698

Text #1

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.7439. Min Act: -0.0000

Data Index: 993325 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.6797. Min Act: -0.0000

Data Index: 1245859 (C4 (Web Text))

Max Activating Token Index: 386

Text #3

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.6388. Min Act: -0.0000

Data Index: 364986 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5832. Min Act: -0.0000

Data Index: 794783 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.6193. Min Act: -0.0000

Data Index: 784234 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.6193. Min Act: -0.0000

Data Index: 1275910 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.6155. Min Act: -0.0000

Data Index: 805507 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5915. Min Act: -0.0000

Data Index: 441325 (C4 (Web Text))

Max Activating Token Index: 754

Text #9

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.6108. Min Act: -0.0000

Data Index: 1202630 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.6213. Min Act: -0.0000

Data Index: 241215 (C4 (Web Text))

Max Activating Token Index: 340

Text #11

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5595. Min Act: -0.0000

Data Index: 883851 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5949. Min Act: -0.0000

Data Index: 377367 (C4 (Web Text))

Max Activating Token Index: 19

Text #13

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5716. Min Act: -0.0000

Data Index: 231314 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5527. Min Act: -0.0000

Data Index: 1041372 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5643. Min Act: -0.0000

Data Index: 761456 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5223. Min Act: -0.0000

Data Index: 408029 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.6289. Min Act: -0.0000

Data Index: 702293 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5833. Min Act: -0.0000

Data Index: 368850 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 0.7439. Min Range: -0.7439

Max Act: 0.5534. Min Act: -0.0000

Data Index: 1121153 (C4 (Web Text))

Max Activating Token Index: 712