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

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

Neuron 788 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0223. Min Range: -1.0223

Max Act: 1.0223. Min Act: -0.0001

Data Index: 238604 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.9568. Min Act: -0.0001

Data Index: 1577039 (Python Code)

Max Activating Token Index: 818

Text #2

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.8320. Min Act: -0.0001

Data Index: 735535 (C4 (Web Text))

Max Activating Token Index: 966

Text #3

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.8143. Min Act: -0.0001

Data Index: 689132 (C4 (Web Text))

Max Activating Token Index: 436

Text #4

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.7938. Min Act: -0.0001

Data Index: 1288081 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.7926. Min Act: -0.0001

Data Index: 778551 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.8803. Min Act: -0.0001

Data Index: 648524 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.7801. Min Act: -0.0001

Data Index: 1190921 (C4 (Web Text))

Max Activating Token Index: 725

Text #8

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.7600. Min Act: -0.0001

Data Index: 927499 (C4 (Web Text))

Max Activating Token Index: 838

Text #9

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.8500. Min Act: -0.0001

Data Index: 8244 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.8104. Min Act: -0.0001

Data Index: 429917 (C4 (Web Text))

Max Activating Token Index: 846

Text #11

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.7091. Min Act: -0.0001

Data Index: 1250098 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.8033. Min Act: -0.0001

Data Index: 654139 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.8034. Min Act: -0.0001

Data Index: 1085714 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.7900. Min Act: -0.0001

Data Index: 1269802 (C4 (Web Text))

Max Activating Token Index: 409

Text #15

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.6914. Min Act: -0.0001

Data Index: 751058 (C4 (Web Text))

Max Activating Token Index: 577

Text #16

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.6764. Min Act: -0.0001

Data Index: 970628 (C4 (Web Text))

Max Activating Token Index: 676

Text #17

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.5694. Min Act: -0.0001

Data Index: 998219 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.6458. Min Act: -0.0001

Data Index: 634283 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 1.0223. Min Range: -1.0223

Max Act: 0.6534. Min Act: -0.0001

Data Index: 310203 (C4 (Web Text))

Max Activating Token Index: 290